© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-4B
    3. 19-TRANSCODER-HP
    4. 5437
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pool
    -0.27
    ingu
    -0.27
    имв
    -0.24
     undercut
    -0.24
     trá»Ŀi
    -0.24
    Symbol
    -0.23
    dress
    -0.23
     stead
    -0.23
     Symbol
    -0.23
     CCTV
    -0.23
    POSITIVE LOGITS
    iquer
    0.26
    nect
    0.25
    ADVERTISEMENT
    0.25
    å¼ºåĽ½
    0.25
    gil
    0.25
    nty
    0.24
    AGER
    0.24
     GLint
    0.24
    ç¥ŀç§ĺ
    0.24
    URING
    0.24
    Activations Density 0.038%

    No Known Activations