© 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. 6684
    Prev
    Next
    INDEX
    Explanations

    code/files

    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
    sWith
    -0.36
    spo
    -0.28
    tons
    -0.28
    ç¥ŀå·ŀ
    -0.28
    sg
    -0.28
    ä¸İåIJ¦
    -0.27
    ajar
    -0.27
    sv
    -0.27
    lington
    -0.26
    ä»ŀ
    -0.26
    POSITIVE LOGITS
    cape
    0.41
    pace
    0.35
    ervice
    0.35
    heet
    0.30
    peak
    0.30
    pawn
    0.30
    paces
    0.30
    erv
    0.29
    peed
    0.29
    quare
    0.29
    Activations Density 6.123%

    No Known Activations