© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 2999
    Prev
    Next
    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash

    references to the lipoprotein(a) biomarker (including its apolipoprotein form) and related terminology, especially in contexts discussing its levels, concentrations, or clinical risk associations.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     widely
    -0.08
     fill
    -0.07
     sustain
    -0.07
    íf
    -0.07
    ritt
    -0.07
    	glm
    -0.07
    Iran
    -0.07
     wider
    -0.07
    反映出
    -0.06
    .tie
    -0.06
    POSITIVE LOGITS
     ENTITY
    0.08
    📏
    0.07
    Lookup
    0.07
     madre
    0.07
    łoży
    0.07
    шение
    0.07
    .agent
    0.07
     hä
    0.07
     owed
    0.06
    .Doc
    0.06
    Activations Density 0.004%

    No Known Activations