© 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. 88990
    Prev
    Next
    INDEX
    Explanations

    code/legal/game documents

    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
    IDGE
    -0.26
     hashing
    -0.26
     ed
    -0.25
     rhet
    -0.25
    iology
    -0.25
    ibus
    -0.25
    photos
    -0.24
    омеÑĢ
    -0.24
    cence
    -0.24
    æĢ»å±Ģ
    -0.24
    POSITIVE LOGITS
    è¯įæĿ¡
    0.27
    产åIJİ
    0.26
    çģĮ
    0.26
    èĤ¡ä»½
    0.26
    æľīæľºä¼ļ
    0.25
    æĪijçļĦå¿ĥ
    0.25
     anxious
    0.25
    èĥĨ
    0.24
    ç¯ĩæĸĩç«ł
    0.24
    íķŃ
    0.24
    Activations Density 0.001%

    No Known Activations