© 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. 8654
    Prev
    Next
    INDEX
    Explanations

    Formal writing and licensing

    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
    åĵªäºĽ
    -0.35
    plural
    -0.31
    å¤ļ家
    -0.31
    éĤ£äºĽ
    -0.30
    è¿ĺæľīä¸ĢäºĽ
    -0.30
    çļĦä¸ĢäºĽ
    -0.29
    åIJĦ级
    -0.29
    åĩłå¼ł
    -0.29
     plural
    -0.28
    åIJĦå¼ı
    -0.28
    POSITIVE LOGITS
    ipo
    0.28
    setLayout
    0.26
    .invoke
    0.26
    ilet
    0.25
    cy
    0.25
    zion
    0.24
    пе
    0.24
    عا
    0.24
    anson
    0.23
    argas
    0.23
    Activations Density 0.060%

    No Known Activations