© 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. 20-TRANSCODER-HP
    7. 108694
    Prev
    Next
    INDEX
    Explanations

    Historical narratives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    uring
    -0.28
    anding
    -0.27
    èĤ²
    -0.27
    pler
    -0.26
    INGTON
    -0.26
    fra
    -0.25
    away
    -0.25
    oids
    -0.25
    Uid
    -0.24
    éģĤ
    -0.24
    POSITIVE LOGITS
    aN
    0.29
    atro
    0.28
    åIJĪæł¼
    0.28
    ä¸Ģ家
    0.28
    æĬ¥åijĬæĺ¾ç¤º
    0.27
    slice
    0.27
    åıijå±ķ模å¼ı
    0.26
     slice
    0.26
    èĥ½åĬĽå¼º
    0.26
    olla
    0.25
    Activations Density 6.428%

    No Known Activations