© 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. 88797
    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
    rels
    -0.27
     constit
    -0.26
     compliment
    -0.25
    å±ķ
    -0.25
    èĩªè´Ł
    -0.24
    logs
    -0.24
    <r
    -0.24
     folding
    -0.24
    acity
    -0.24
    spl
    -0.24
    POSITIVE LOGITS
     vas
    0.27
    åįģä¸īå±Ĭ
    0.23
     pu
    0.23
    继ç»Ńä¿ĿæĮģ
    0.23
    çĤ
    0.23
     america
    0.23
    Motor
    0.23
    getManager
    0.23
    ä¸į顾
    0.22
    æĸ°æĹ¶ä»£
    0.22
    Activations Density 0.031%

    No Known Activations

    This feature has no known activations.