© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 7-RESID-POST-AA
    11. 42368
    Prev
    Next
    INDEX
    Explanations

    de

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nen
    -0.07
    菖
    -0.07
    获批
    -0.06
    keyword
    -0.06
    赳
    -0.06
    有了
    -0.06
    しょう
    -0.06
    /GPL
    -0.06
    筶
    -0.06
    xon
    -0.06
    POSITIVE LOGITS
    (ai
    0.08
    _library
    0.07
     Entertainment
    0.07
    _reward
    0.07
    /network
    0.07
     DXGI
    0.07
    anda
    0.07
    _salt
    0.07
     코드
    0.07
    école
    0.07
    Activations Density 0.047%

    No Known Activations