Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 11-TRANSCODER-HP
    4. 46293
    Prev
    Next
    INDEX
    Explanations

    medicine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_11.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.11.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thr
    -0.27
     pronto
    -0.27
     linguistic
    -0.26
    -letter
    -0.26
     letters
    -0.26
    ç»ĵæĻ¶
    -0.26
    tright
    -0.25
    rim
    -0.25
     Gift
    -0.25
    çĶŁäº§èĥ½åĬĽ
    -0.24
    POSITIVE LOGITS
    ä¸įéĶĻ
    0.28
    cla
    0.26
    客æµģ
    0.26
    è§£æĶ¾åĨĽ
    0.26
    .DEFINE
    0.25
    çĸ²åĬ³
    0.24
     ArgumentOutOfRangeException
    0.24
    éĢĢè¿ĺ
    0.23
    æ±°
    0.23
    ¡°
    0.23
    Activations Density 0.030%

    No Known Activations