© 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. 7917
    Prev
    Next
    INDEX
    Explanations

    Patents

    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
    许
    -0.28
    ·¨
    -0.27
    heard
    -0.26
    åı¯è§Ĩ
    -0.26
    theid
    -0.25
     Amar
    -0.25
    nist
    -0.25
    âĿ¥
    -0.25
    mts
    -0.24
    bole
    -0.24
    POSITIVE LOGITS
    åĩ¡æľ¬ç½ij
    0.28
    bart
    0.26
     preval
    0.25
    RowCount
    0.25
    inv
    0.25
    ç§ģèIJ¥
    0.25
     {}).
    0.25
    .long
    0.25
    ä¸Ĭåįĩ
    0.25
     оÑĤзÑĭв
    0.24
    Activations Density 0.128%

    No Known Activations