© 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. 39442
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     trailed
    -0.28
    æĭ¥æĬ¤
    -0.28
    ä¸İä¼Ĺ
    -0.27
    keeper
    -0.26
    nan
    -0.26
     keeper
    -0.26
     dor
    -0.24
    aged
    -0.24
    mage
    -0.24
    association
    -0.23
    POSITIVE LOGITS
    客æĪ·æıIJä¾Ľ
    0.31
     problem
    0.28
     vezes
    0.27
    .problem
    0.27
     diam
    0.26
     }//
    0.25
     Clause
    0.25
     diá
    0.25
    æ±
    0.25
    ém
    0.24
    Activations Density 1.054%

    No Known Activations