© 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. 9-TRANSCODER-HP
    7. 29601
    Prev
    Next
    INDEX
    Explanations

    spent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sons
    -0.28
    .inc
    -0.27
    ermann
    -0.26
    æݨéĢģ
    -0.26
    xcc
    -0.26
    -inc
    -0.25
    omaly
    -0.25
    aged
    -0.25
     softened
    -0.25
    eways
    -0.24
    POSITIVE LOGITS
    */,
    0.26
    æĬ¥è®°èĢħ
    0.26
    ellan
    0.26
    羡
    0.25
    éĵºè®¾
    0.25
    cern
    0.25
    */,↵
    0.25
    oleon
    0.24
    éĿ¢åħ·
    0.24
    inde
    0.24
    Activations Density 0.657%

    No Known Activations