© 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. 32-TRANSCODER-HP
    7. 41867
    Prev
    Next
    INDEX
    Explanations

    Artificial and synthetic

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aned
    -0.26
     Abe
    -0.25
    ä¸Ĭæĸ¹
    -0.25
    çĿ¹
    -0.24
    à¸ĵ
    -0.24
    ç«ĻçĿĢ
    -0.24
    .mainloop
    -0.23
    ä¸ĭ车
    -0.23
    OLER
    -0.23
     delegation
    -0.23
    POSITIVE LOGITS
     artificial
    1.23
    人工
    1.19
     Artificial
    1.08
     synthetic
    0.94
     art
    0.89
     иÑģкÑĥÑģÑģÑĤв
    0.88
    Art
    0.87
    人éĢł
    0.85
    art
    0.83
     artificially
    0.82
    Activations Density 0.001%

    No Known Activations