© 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. 15-RESID-POST-AA
    11. 71664
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Negative Logits
     striking
    -0.07
    强国
    -0.07
    

↵
    -0.07
    vers
    -0.07
    ない
    -0.07
     indiscrim
    -0.06
    펑
    -0.06
    \'
    -0.06
    黄埔
    -0.06
     ambos
    -0.06
    POSITIVE LOGITS
     Qualified
    0.08
    内饰
    0.07
    Об
    0.07
    Todd
    0.07
    _nested
    0.07
    Designed
    0.06
    locals
    0.06
     הטבע
    0.06
     maturity
    0.06
     малыш
    0.06
    Activations Density 0.087%

    No Known Activations