© 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. 53245
    Prev
    Next
    INDEX
    Explanations

    quitting

    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
     resembles
    -0.07
     fine
    -0.07
     ан
    -0.07
     jewish
    -0.07
    艰巨
    -0.07
     Dh
    -0.07
    自动驾驶
    -0.06
    ís
    -0.06
    CH
    -0.06
     Bella
    -0.06
    POSITIVE LOGITS
    依然
    0.08
    Neal
    0.07
    واقع
    0.07
    넋
    0.07
    这一刻
    0.06
    (dat
    0.06
    ками
    0.06
     nonce
    0.06
     Sacred
    0.06
     pane
    0.06
    Activations Density 0.024%

    No Known Activations