© 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. 131121
    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
    åķĨæĬ¥
    -0.31
    转身
    -0.29
    æīĭå¥Ĺ
    -0.27
    åĨħå¿ĥçļĦ
    -0.26
    åĮĸè¿Ľç¨ĭ
    -0.26
    icts
    -0.26
    -map
    -0.25
    çļĦä¿¡å¿ĥ
    -0.24
    edo
    -0.23
    çĽĶ
    -0.23
    POSITIVE LOGITS
    olly
    0.27
    asan
    0.27
    Łèĥ½
    0.26
    ought
    0.26
    (Optional
    0.25
    ä¸įæŃ¢
    0.24
    asset
    0.24
     compulsory
    0.24
    æĤ¬
    0.23
    anan
    0.23
    Activations Density 0.010%

    No Known Activations

    This feature has no known activations.