© 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. 48754
    Prev
    Next
    INDEX
    Explanations

    Class

    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
     mug
    -0.07
     Wash
    -0.07
    תואר
    -0.07
    .Typed
    -0.06
     targeted
    -0.06
     추진
    -0.06
    并将
    -0.06
    熬
    -0.06
     מעט
    -0.06
    窗帘
    -0.06
    POSITIVE LOGITS
     prevailing
    0.07
    𝕐
    0.07
    timeout
    0.07
     الإسلامي
    0.07
    (':')[
    0.07
    𝐒
    0.07
    iom
    0.06
    ൽ
    0.06
    ()>↵
    0.06
     Celtic
    0.06
    Activations Density 0.007%

    No Known Activations