© 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. 25-TRANSCODER-HP
    7. 108466
    Prev
    Next
    INDEX
    Explanations

    code and URLs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sé
    -0.29
     buffering
    -0.29
     **
    -0.28
    kah
    -0.27
     b
    -0.26
    ä¼ł
    -0.26
    NewProp
    -0.26
     own
    -0.26
     proposition
    -0.25
     wonder
    -0.25
    POSITIVE LOGITS
    åĩºæ±Ĺ
    0.28
    onChange
    0.25
    oley
    0.25
    èĻļå¼±
    0.25
     Koreans
    0.24
    .intellij
    0.24
    ADVERTISEMENT
    0.24
    .onChange
    0.23
    ä¸įåħģ许
    0.23
    onest
    0.23
    Activations Density 0.026%

    No Known Activations