© 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. 9-TRANSCODER-HP
    7. 30317
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    两æĿ¡
    -0.27
    ongan
    -0.26
    Solid
    -0.26
    CardContent
    -0.25
    VERIFY
    -0.25
    wipe
    -0.24
    å¿ĥåĬ¨
    -0.24
    itaire
    -0.24
    忸
    -0.23
     Reported
    -0.23
    POSITIVE LOGITS
    禺
    0.29
    åľ¨çº¿
    0.28
     pres
    0.26
    å¢ŀ
    0.26
    çIJĨ
    0.25
    空
    0.25
    çķľ
    0.25
    azzi
    0.25
    èķĸ
    0.24
     hu
    0.24
    Activations Density 0.573%

    No Known Activations