© 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. 25616
    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
    oce
    -0.29
    bv
    -0.29
     Moor
    -0.27
     Cause
    -0.27
    ç¿ĺ
    -0.27
    akov
    -0.27
     entitled
    -0.26
    ä»ĸçŁ¥éģĵ
    -0.26
    prove
    -0.26
    bdd
    -0.25
    POSITIVE LOGITS
    ENSITY
    0.27
    omy
    0.27
    æ±°
    0.25
    ombie
    0.25
     Manuals
    0.24
    å¥Ĥ
    0.24
    \Php
    0.24
    顾
    0.23
    æİī
    0.23
    家åħ¬åı¸
    0.23
    Activations Density 0.001%

    No Known Activations