© 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. 12204
    Prev
    Next
    INDEX
    Explanations

    segreg

    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
    َا
    -0.07
     השונים
    -0.07
     Bella
    -0.07
     Dop
    -0.07
    読んで
    -0.07
     dizzy
    -0.07
     fout
    -0.07
     visit
    -0.07
    男方
    -0.07
    Տ
    -0.07
    POSITIVE LOGITS
    --
    0.07
    ,<
    0.07
    纂
    0.07
    .metric
    0.06
    -g
    0.06
    十九
    0.06
    نية
    0.06
    -wing
    0.06
     Religion
    0.06
     skills
    0.06
    Activations Density 0.003%

    No Known Activations