© 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. 88873
    Prev
    Next
    INDEX
    Explanations

    Punctuation

    np_max-act · gemini-2.0-flash
    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
     desn
    -0.28
    äºĨ好
    -0.27
    ä½ĵ系建设
    -0.26
    çĶļèĩ³æĺ¯
    -0.26
    èIJ¥åĪ©
    -0.25
    è¾ĥ强çļĦ
    -0.25
    æĩĤ
    -0.25
    æ±ĩèģļ
    -0.25
    å¾Ģå¾Ģä¼ļ
    -0.24
    çŃĿ
    -0.24
    POSITIVE LOGITS
    请注æĦı
    0.32
    ffa
    0.25
    注æĦı
    0.24
    ergarten
    0.24
    ("${
    0.23
    иÑĤе
    0.23
    osci
    0.23
    ëĨĢ
    0.23
     Ins
    0.23
     clue
    0.23
    Activations Density 0.005%

    No Known Activations