© 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. 11-RESID-POST-AA
    11. 83129
    Prev
    Next
    INDEX
    Explanations

    fiss

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     getattr
    -0.08
     centered
    -0.07
    online
    -0.07
    新材料
    -0.07
     Founder
    -0.07
     feminist
    -0.07
    /bootstrap
    -0.06
    弄
    -0.06
     evangelical
    -0.06
    /master
    -0.06
    POSITIVE LOGITS
    0.09
    .expires
    0.07
    	IL
    0.07
     fax
    0.07
     plano
    0.07
     hỏ
    0.07
     המציאות
    0.07
    Bulk
    0.07
    Fs
    0.07
     Боль
    0.07
    Activations Density 0.001%

    No Known Activations