© 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. 23-TRANSCODER-HP
    7. 23633
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    enario
    -0.29
    cel
    -0.27
    patch
    -0.27
    ä¹Łåı¯ä»¥
    -0.27
    èĢģ人家
    -0.26
    /GL
    -0.26
     patch
    -0.25
    大åĬĽåıijå±ķ
    -0.25
     substitution
    -0.24
    .se
    -0.24
    POSITIVE LOGITS
    èħ®
    0.29
    åĽ½åĬ¡
    0.28
     /*#__
    0.28
    ë¦ĩ
    0.27
    NDER
    0.27
    éré
    0.26
     unders
    0.26
    getDoctrine
    0.26
    uant
    0.25
    enti
    0.25
    Activations Density 0.002%

    No Known Activations