© 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. 14-TRANSCODER-HP
    7. 39429
    Prev
    Next
    INDEX
    Explanations

    Product descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    è¿Ļ件
    -0.27
    Hist
    -0.27
    lite
    -0.27
     purchasers
    -0.27
    éºŁ
    -0.26
    çļĦåĮºåĪ«
    -0.26
    dee
    -0.26
    åIJĥè¿ĩ
    -0.26
     Getty
    -0.26
    顾éĹ®
    -0.25
    POSITIVE LOGITS
     Thảo
    0.29
    lest
    0.26
    æµİ
    0.24
    antas
    0.24
     implode
    0.24
    æŃ¥
    0.24
    åħ¨åijĺ
    0.23
    驼
    0.23
    logan
    0.23
    heim
    0.23
    Activations Density 0.179%

    No Known Activations