© 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. 151216
    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
    /ion
    -0.29
    istant
    -0.28
    åħ¨å¤©
    -0.26
    人士
    -0.26
    __',
    -0.25
    ç´¯äºĨ
    -0.25
    æĸ°åŁİ
    -0.25
    esium
    -0.25
    .share
    -0.25
    稽
    -0.25
    POSITIVE LOGITS
     Sup
    0.27
    秣
    0.24
     words
    0.24
    mak
    0.24
     feet
    0.23
     merc
    0.23
    æĢ§åĴĮ
    0.23
    Nullable
    0.23
     Words
    0.23
    át
    0.23
    Activations Density 0.134%

    No Known Activations

    This feature has no known activations.