© 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. 113338
    Prev
    Next
    INDEX
    Explanations

    seeing or hearing

    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
    몫
    -0.07
    /n
    -0.07
    툭
    -0.06
    
    -0.06
    *v
    -0.06
    افظ
    -0.06
    忽视
    -0.06
     götür
    -0.06
     voksen
    -0.06
     influenced
    -0.06
    POSITIVE LOGITS
    _ASSERT
    0.07
     borrow
    0.07
    ;",
    0.07
     estr
    0.07
    ,...↵↵
    0.06
    .parseDouble
    0.06
     <<↵
    0.06
     Ка
    0.06
    内心的
    0.06
    民主
    0.06
    Activations Density 0.054%

    No Known Activations