© 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. 24-TRANSCODER-HP
    7. 149403
    Prev
    Next
    INDEX
    Explanations

    Non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    _mt
    -0.29
    .eng
    -0.26
     manifest
    -0.26
    ç¼ĸåı·
    -0.25
    feeds
    -0.25
    .ft
    -0.24
    ä¸īè§Ĵ
    -0.24
    jÄħ
    -0.24
     nomine
    -0.24
    MT
    -0.23
    POSITIVE LOGITS
    ç´§
    0.27
    åį¯
    0.25
    ogenic
    0.25
    åѦéĹ®
    0.25
    è¿Ľåıĸ
    0.25
    å¦ĥ
    0.24
    angep
    0.24
    æ¾Į
    0.24
     Vik
    0.24
    è¯ļæĦı
    0.24
    Activations Density 0.190%

    No Known Activations