© 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. 149401
    Prev
    Next
    INDEX
    Explanations

    technical language

    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
    Xd
    -0.27
    æł¡
    -0.25
    æĹ¥çĶµ
    -0.25
    éĻ¢
    -0.24
    reed
    -0.24
     dotted
    -0.24
    产ä¸ļ
    -0.24
    ~/
    -0.24
     special
    -0.23
    _protocol
    -0.23
    POSITIVE LOGITS
     ÐļÑĥ
    0.28
     CFL
    0.26
     cue
    0.25
    idth
    0.25
    å©ļåIJİ
    0.25
     ePub
    0.24
    .Expressions
    0.24
     watch
    0.24
    ercul
    0.24
    åĿĢ
    0.23
    Activations Density 0.276%

    No Known Activations