© 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. 12-TRANSCODER-HP
    7. 22485
    Prev
    Next
    INDEX
    Explanations

    breasts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anko
    -0.29
    çªĿ
    -0.27
    ponent
    -0.26
    pecially
    -0.25
    é¢ľèī²
    -0.25
    åĨįè§ģ
    -0.25
    ç¿ģ
    -0.24
    ÙĩÙĨ
    -0.24
    æĤ¯
    -0.24
     espec
    -0.24
    POSITIVE LOGITS
    ä¸Ģè´¯
    0.30
    æľ¬æĬ¥
    0.28
    èªķ
    0.27
     na
    0.26
     gou
    0.25
     resid
    0.24
     alc
    0.24
     fueled
    0.23
     CONTR
    0.23
     bil
    0.23
    Activations Density 0.003%

    No Known Activations