© 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. 5234
    Prev
    Next
    INDEX
    Explanations

    articles

    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
     guilty
    -0.28
     Guaranteed
    -0.28
     Arguments
    -0.27
     couldn
    -0.27
    éĤ£æ¬¡
    -0.27
    IDA
    -0.27
     Äijiá»ĥn
    -0.26
    çļĦè§ĤçĤ¹
    -0.25
     denied
    -0.25
     arguments
    -0.24
    POSITIVE LOGITS
    档次
    0.27
    ä¸Ĭä¸ĭ游
    0.27
    ä¸Ĭ游
    0.27
    ellow
    0.26
    cut
    0.25
    STALL
    0.25
    /Layout
    0.24
    æĴŃ
    0.24
    ós
    0.24
     genital
    0.24
    Activations Density 0.013%

    No Known Activations