© 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. 5817
    Prev
    Next
    INDEX
    Explanations

    Online 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
    tie
    -0.25
    åģļå·¥
    -0.25
    WM
    -0.25
    intage
    -0.24
    -date
    -0.24
    ä½łæĺ¯
    -0.23
    urre
    -0.23
    WR
    -0.23
    e
    -0.23
     actually
    -0.23
    POSITIVE LOGITS
     mont
    0.28
    sov
    0.27
    INGS
    0.27
    osas
    0.26
    ç»İ
    0.26
    çļĦèĦļæŃ¥
    0.25
    uga
    0.24
     shells
    0.24
    -gnu
    0.24
    -elements
    0.23
    Activations Density 0.051%

    No Known Activations