© 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. 5412
    Prev
    Next
    INDEX
    Explanations

    Research literature

    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
    åłµ
    -0.26
     bark
    -0.25
    ãĤīãģĽ
    -0.24
    iday
    -0.24
    hti
    -0.24
    æĸĭ
    -0.24
    éģĵçIJĨ
    -0.24
     liv
    -0.24
     Bark
    -0.24
    è¯Ŀé¢ĺ
    -0.23
    POSITIVE LOGITS
    æĭ§
    0.26
    满æĢĢ
    0.25
     Trem
    0.24
    离
    0.24
     Strateg
    0.24
    any
    0.23
    æĮīè§Ħå®ļ
    0.23
    _win
    0.23
     gu
    0.23
    itle
    0.23
    Activations Density 0.074%

    No Known Activations