© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6772
    Prev
    Next
    INDEX
    Explanations

    Code, special characters

    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
    ColumnType
    -0.28
    ç®IJ
    -0.28
     spans
    -0.28
     âĨĴ↵↵
    -0.27
    iggins
    -0.27
    “↵↵
    -0.26
    åı¯èĥ½åŃĺåľ¨
    -0.26
    neys
    -0.25
    cycl
    -0.25
    ’↵↵
    -0.25
    POSITIVE LOGITS
     {}.
    0.29
    ector
    0.28
    .↵
    0.28
    [].
    0.27
    sworth
    0.27
     [].
    0.27
    .',
    0.27
    .").
    0.27
    .");↵
    0.27
    .).
    0.26
    Activations Density 0.077%

    No Known Activations