© 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. 88978
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    VisualStyleBackColor
    -0.08
    rema
    -0.07
    :end
    -0.07
    ictim
    -0.07
    *))
    -0.07
     чего
    -0.07
    _modes
    -0.07
     Html
    -0.07
     inducing
    -0.07
    -billion
    -0.07
    POSITIVE LOGITS
     Zach
    0.07
    gt
    0.07
     diret
    0.07
    世界各国
    0.07
    回国
    0.07
    吳
    0.07
    ⚅
    0.07
    PI
    0.07
    科学家
    0.07
    馬
    0.07
    Activations Density 0.054%

    No Known Activations