© 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. 95022
    Prev
    Next
    INDEX
    Explanations

    coding/technical context

    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
    unge
    -0.30
     compile
    -0.26
    å¥ĸ
    -0.24
    artner
    -0.24
    öst
    -0.24
    ova
    -0.24
    ancia
    -0.24
     trend
    -0.24
    irim
    -0.24
    [mask
    -0.23
    POSITIVE LOGITS
    piece
    0.28
    æĿ¡
    0.25
     condition
    0.25
    IDEO
    0.24
     WTF
    0.24
    æ¢Ŀ件
    0.24
    æŃ¢
    0.24
     lips
    0.24
     provisional
    0.24
    pieces
    0.24
    Activations Density 0.000%

    No Known Activations