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. 46896
    Prev
    Next
    INDEX
    Explanations

    effects

    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
    塵
    -0.30
    å°ĺ
    -0.28
     diam
    -0.28
    zig
    -0.27
    ä¸ļæĢģ
    -0.26
     Lesson
    -0.26
    _fast
    -0.25
    èĥĻ
    -0.25
    yen
    -0.25
    _collision
    -0.25
    POSITIVE LOGITS
    kp
    0.28
     GPL
    0.27
    饶
    0.27
    -hearted
    0.26
     tq
    0.26
     COPYING
    0.25
    oples
    0.25
    entic
    0.25
    纯
    0.25
    æ°´éĿ¢
    0.25
    Activations Density 0.175%

    No Known Activations