© 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. 129345
    Prev
    Next
    INDEX
    Explanations

    Actions, results, scientific process

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æĿ¥æºIJäºİ
    -0.35
    æºIJäºİ
    -0.33
    æĿ¥èĩªäºİ
    -0.30
    ĽĦ
    -0.30
    çĶ±ä¸ŃåĽ½
    -0.29
    æĺ¯çĶ±
    -0.29
    æ³¼
    -0.29
    lator
    -0.28
    è¹Ī
    -0.27
    豪
    -0.27
    POSITIVE LOGITS
     moreover
    0.26
    å¼Ģ车
    0.26
     Moreover
    0.25
    ża
    0.25
    rq
    0.24
    cq
    0.24
    ä¸Ķ
    0.24
    æ¼Ķ示
    0.23
    oro
    0.23
    æĪĹ
    0.23
    Activations Density 17.106%

    No Known Activations