© 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. 19-RESID-POST-AA
    11. 66518
    Prev
    Next
    INDEX
    Explanations

    .test

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Nhi
    -0.07
    ᆯ
    -0.07
    fragment
    -0.07
    跟随
    -0.07
     Den
    -0.07
    ,G
    -0.07
     Astr
    -0.06
     Fellow
    -0.06
    ゛
    -0.06
     describe
    -0.06
    POSITIVE LOGITS
    有意思的
    0.06
     sırasında
    0.06
    _Interface
    0.06
    IntegerField
    0.06
     societal
    0.06
    战士职业
    0.06
    _time
    0.06
    変わ
    0.06
    ьер
    0.06
    口感
    0.06
    Activations Density 0.000%

    No Known Activations