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

    Neuronpedia

    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. 28681
    Prev
    Next
    INDEX
    Explanations

    too good to be true

    np_max-act · gemini-2.0-flash
    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
    清醒
    -0.07
    ueling
    -0.07
    .rs
    -0.07
    呵护
    -0.07
    /install
    -0.07
    我が
    -0.06
    vor
    -0.06
     gamers
    -0.06
    	glm
    -0.06
    .slot
    -0.06
    POSITIVE LOGITS
    frauen
    0.07
     statements
    0.07
     userdata
    0.07
     headline
    0.07
    ."'
    0.06
     antibodies
    0.06
     dla
    0.06
    _tags
    0.06
     nephew
    0.06
    significant
    0.06
    Activations Density 0.035%

    No Known Activations