© 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. 33-TRANSCODER-HP
    7. 54483
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¾Ĺå¤ļ
    -0.30
    stein
    -0.28
     twenties
    -0.25
    /API
    -0.25
    éŁ¿
    -0.25
    uiltin
    -0.24
    æ¾³
    -0.24
     speeds
    -0.23
    adelphia
    -0.23
    ijken
    -0.23
    POSITIVE LOGITS
    æĿ¡
    0.26
    usu
    0.25
    å±ij
    0.25
    ç»ı纬
    0.25
    æµ£
    0.25
    åĪ®
    0.25
    neh
    0.24
     cookie
    0.24
    漫
    0.24
    adb
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.