© 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. 7301
    Prev
    Next
    INDEX
    Explanations

    Summaries of 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
    çķ´
    -0.28
     later
    -0.25
    课é¢ĺ
    -0.25
     delays
    -0.24
    cai
    -0.24
    ellar
    -0.23
    ertility
    -0.23
    emade
    -0.23
     später
    -0.23
    later
    -0.23
    POSITIVE LOGITS
    oxy
    0.25
    ä¸ľè¥¿
    0.25
     Ly
    0.24
    ODO
    0.24
    Ly
    0.24
    hen
    0.24
     gust
    0.23
     Output
    0.23
     slips
    0.23
    èIJĿ
    0.23
    Activations Density 0.023%

    No Known Activations