© 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. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 56586
    Prev
    Next
    INDEX
    Explanations

    Bro

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æħ£
    -0.26
    rou
    -0.24
    imid
    -0.24
    åģıå·®
    -0.24
     superf
    -0.24
    åĪĨå±Ģ
    -0.24
    breaking
    -0.23
    friend
    -0.23
    iances
    -0.23
    ç§ī
    -0.23
    POSITIVE LOGITS
    _annotations
    0.26
     moc
    0.26
    zan
    0.26
     turnout
    0.25
     velocity
    0.25
    culos
    0.24
    åijĬè¯īä»ĸ
    0.24
    mousemove
    0.24
    ç»İ
    0.24
    åĪĿ级
    0.24
    Activations Density 1.228%

    No Known Activations