© 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. 149253
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     tallest
    -0.26
    bcc
    -0.25
    orsk
    -0.24
    è¾ĸ
    -0.24
    inherit
    -0.23
    MR
    -0.23
    ä¸Ńæľī
    -0.23
    æİ£
    -0.23
    rored
    -0.23
    vos
    -0.23
    POSITIVE LOGITS
    arat
    0.26
     Blaze
    0.25
     Celebration
    0.25
    æīĵ
    0.25
    nes
    0.24
    åı¯ä»¥çĽ´æİ¥
    0.24
     transmitting
    0.24
    åı¯ä»¥åľ¨
    0.24
     supposed
    0.23
    éĢĢè¿ĺ
    0.23
    Activations Density 0.207%

    No Known Activations

    This feature has no known activations.