© 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
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5949
    Prev
    Next
    INDEX
    Explanations

    Code/Programming

    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
    iaz
    -0.27
    -fl
    -0.27
    éķĽ
    -0.26
    <option
    -0.26
    extract
    -0.25
    èĵĭ
    -0.24
    å²IJ
    -0.24
     reload
    -0.23
    gl
    -0.23
    obi
    -0.23
    POSITIVE LOGITS
    Ĺı
    0.24
     keyed
    0.24
    ç±»åĪ«
    0.24
    çľģå¸Ĥ
    0.24
     RootState
    0.24
    Enumerable
    0.24
    æĢ¿
    0.23
    ')+
    0.23
    imoto
    0.23
    QC
    0.23
    Activations Density 0.711%

    No Known Activations