© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7686
    Prev
    Next
    INDEX
    Explanations

    digits

    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
    èĦ¯
    -0.28
    以èĩ´
    -0.26
    &w
    -0.26
    blink
    -0.26
    éĤij
    -0.26
    friend
    -0.25
    éĢĽè¡Ĺ
    -0.25
    bilt
    -0.24
    uur
    -0.24
    è¡Ĺ
    -0.23
    POSITIVE LOGITS
    inee
    0.29
    èĢĮæĿ¥
    0.25
    Alive
    0.24
    attering
    0.24
    едÑĮ
    0.24
    inite
    0.24
    BREAK
    0.23
    oration
    0.23
    ONO
    0.23
    ‘
    0.23
    Activations Density 0.017%

    No Known Activations