© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 141302
    Prev
    Next
    INDEX
    Explanations

    Information, resources, assistance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rou
    -0.28
    iliar
    -0.27
    æĸ¹éĿ¢çļĦ
    -0.26
    åĩĨç¡®
    -0.26
    atus
    -0.26
    imately
    -0.25
    ÅŁt
    -0.25
    naments
    -0.24
    åªŀ
    -0.24
    oris
    -0.24
    POSITIVE LOGITS
    _own
    0.27
    éģĤ
    0.26
    åIJĮæĹ¶ä¹Ł
    0.25
     chiefly
    0.24
    abbage
    0.24
    .diag
    0.24
    åijĨ
    0.23
    NET
    0.23
     Retrie
    0.23
     além
    0.23
    Activations Density 8.146%

    No Known Activations