© 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. 5822
    Prev
    Next
    INDEX
    Explanations

    and/or

    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
    .SERVER
    -0.26
    å®Ŀè´Ŀ
    -0.25
    oxetine
    -0.25
    olland
    -0.25
    untas
    -0.24
     au
    -0.23
    rawler
    -0.23
    èĵĭ
    -0.23
     gross
    -0.23
    çļĸ
    -0.23
    POSITIVE LOGITS
    ä»İå°ıå°±
    0.25
    çĤ½
    0.24
    åıĮéĩį
    0.24
     zes
    0.24
    abouts
    0.24
    dater
    0.24
    é¢ijé¢ij
    0.23
    åªĴ
    0.23
    entifier
    0.23
    onso
    0.23
    Activations Density 0.071%

    No Known Activations