© 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. 86983
    Prev
    Next
    INDEX
    Explanations

    Patent numbers

    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
    DES
    -0.31
    Magn
    -0.28
     meanwhile
    -0.26
    ucid
    -0.25
    els
    -0.25
    å¹´æĿ¥
    -0.25
    icits
    -0.25
    Ø°ÙĬ
    -0.25
    uffers
    -0.24
     dra
    -0.24
    POSITIVE LOGITS
    ç®ĹäºĨ
    0.26
     scraper
    0.26
    ç®Ĺ
    0.25
    ëŁ¼
    0.25
    ảnh
    0.25
     privacy
    0.24
    失败
    0.24
    åĪĨ管
    0.24
    çĵ¢
    0.24
    å°ģ建
    0.24
    Activations Density 0.011%

    No Known Activations