© 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. 41529
    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
    翳
    -0.25
    å·²åľ¨
    -0.25
    _penalty
    -0.25
     ì°
    -0.25
    Young
    -0.24
    è£Ķ
    -0.24
    os
    -0.24
     buried
    -0.23
    åľ¨äº¬
    -0.23
     Procedure
    -0.23
    POSITIVE LOGITS
    oras
    0.29
    èĥ½åĬĽå¼º
    0.27
    ku
    0.25
    :mysql
    0.25
    æ¡·
    0.25
    phasis
    0.24
    WARE
    0.24
    fills
    0.24
    anced
    0.24
    urus
    0.23
    Activations Density 2.256%

    No Known Activations