© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 30-TRANSCODER-HP
    7. 94917
    Prev
    Next
    INDEX
    Explanations

    numbers written as words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    dings
    -0.31
     variables
    -0.28
     bonds
    -0.28
    forge
    -0.27
    lasses
    -0.26
     indices
    -0.26
     destinations
    -0.26
    onds
    -0.25
     buttons
    -0.25
     vertices
    -0.25
    POSITIVE LOGITS
     ws
    0.31
    raction
    0.29
    /gallery
    0.26
    BED
    0.25
    çļĦä¸ĢéĿ¢
    0.25
    è¡ĮåĬ¨
    0.25
     Woodward
    0.24
    亶
    0.24
    çļĦ人çī©
    0.24
    lane
    0.24
    Activations Density 0.874%

    No Known Activations