© 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. 22-TRANSCODER-HP
    7. 131233
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    wise
    -0.28
    åĪĨ
    -0.27
    itle
    -0.27
    mg
    -0.26
     techn
    -0.25
    .cpp
    -0.24
    _IRQn
    -0.24
    满
    -0.24
     belt
    -0.24
     mark
    -0.24
    POSITIVE LOGITS
    =head
    0.29
    itionally
    0.28
     reputed
    0.27
    oram
    0.27
    ä¸ĩæĪ·
    0.27
    èĦijè¢ĭ
    0.27
    ç³Ĺ
    0.26
    大åĵ¥
    0.26
    ç¶
    0.26
    quire
    0.25
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.