© 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. 5721
    Prev
    Next
    INDEX
    Explanations

    Street abbreviations

    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
    Sensitive
    -0.29
    icap
    -0.24
    ä½ľèĢħæīĢæľī
    -0.24
    ijo
    -0.24
    ograms
    -0.24
     quo
    -0.24
    å½ĵåľ°æĶ¿åºľ
    -0.23
    htable
    -0.23
    patches
    -0.23
     Identified
    -0.23
    POSITIVE LOGITS
    odash
    0.28
    .Tx
    0.27
    /TR
    0.25
    вл
    0.25
    åĢŁ
    0.24
    ç¨Ķ
    0.24
    åĩ¡æĺ¯
    0.24
    .INSTANCE
    0.24
    è¿Ŀåıį
    0.24
    istung
    0.24
    Activations Density 0.037%

    No Known Activations