© 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. 30-TRANSCODER-HP
    7. 97163
    Prev
    Next
    INDEX
    Explanations

    code comments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æĶ¾è¿Ľ
    -0.29
    é¹Ń
    -0.29
    /mat
    -0.28
     asympt
    -0.28
    ighton
    -0.26
     cuff
    -0.26
    覺
    -0.26
    æī«
    -0.25
    åı·çłģ
    -0.25
    åĩĨåħ¥
    -0.25
    POSITIVE LOGITS
    æİ¥
    0.34
    itable
    0.27
    wp
    0.27
    æĸ¹åIJij
    0.27
    UNCH
    0.26
    奢ä¾Īåĵģ
    0.26
    ha
    0.26
    dp
    0.25
    et
    0.25
    js
    0.25
    Activations Density 0.783%

    No Known Activations