© 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. 63858
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     recreational
    -0.07
     dopo
    -0.07
     hod
    -0.07
     wellness
    -0.07
     العالمية
    -0.07
     holy
    -0.06
     ADC
    -0.06
     Barn
    -0.06
     universal
    -0.06
     |_
    -0.06
    POSITIVE LOGITS
    ケー
    0.08
    谒
    0.08
    ьте
    0.07
    進
    0.07
    �
    0.07
    잍
    0.07
    メール
    0.07
    Insets
    0.07
    ﺋ
    0.07
    gressor
    0.07
    Activations Density 0.001%

    No Known Activations