© 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. 24-TRANSCODER-HP
    7. 149663
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inho
    -0.26
     Contribution
    -0.25
    phet
    -0.25
    phan
    -0.25
     Contributions
    -0.25
    pur
    -0.24
    åħį责声æĺİ
    -0.24
    eph
    -0.24
    ServletResponse
    -0.24
    abouts
    -0.24
    POSITIVE LOGITS
    çľĭå¾Ĺ
    0.31
    éĻ¢
    0.30
    è¿Łè¿Ł
    0.28
     unthinkable
    0.27
    æł·çļĦ
    0.25
    好çļĦ
    0.25
    SCRIPT
    0.25
    è´°
    0.24
    etz
    0.24
    cci
    0.24
    Activations Density 0.393%

    No Known Activations

    This feature has no known activations.