© 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. 30364
    Prev
    Next
    INDEX
    Explanations

    change

    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
     ster
    -0.29
    renched
    -0.26
    mare
    -0.26
    ecer
    -0.25
    STER
    -0.25
    phin
    -0.25
    åĿļ
    -0.24
    æ´ĭ
    -0.24
    gone
    -0.24
    gettext
    -0.23
    POSITIVE LOGITS
    åİŁçIJĨ
    0.30
    -rays
    0.26
    åģľå·¥
    0.25
    åģľ
    0.25
    ีà¹ī
    0.24
    ictionaries
    0.24
     //~
    0.24
    åIJĬ顶
    0.23
    è¡Įä¸ļ
    0.23
     NDP
    0.23
    Activations Density 1.366%

    No Known Activations