© 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. 2220
    Prev
    Next
    INDEX
    Explanations

    locations

    np_max-act · gemini-2.0-flash

    structured biographical and document metadata, especially professional titles, education credentials, dates, locations, and quantitative figures.

    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
    циальн
    -0.07
    ۂ
    -0.07
    pecia
    -0.07
     comply
    -0.07
    痈
    -0.06
    猃
    -0.06
     Science
    -0.06
     intimid
    -0.06
    hind
    -0.06
     induce
    -0.06
    POSITIVE LOGITS
     rever
    0.07
    	container
    0.07
    Drag
    0.07
    𝖚
    0.07
    łam
    0.07
     Jean
    0.06
    .Buffered
    0.06
    Unload
    0.06
     mogła
    0.06
    麽
    0.06
    Activations Density 0.797%

    No Known Activations