© 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. 112910
    Prev
    Next
    INDEX
    Explanations

    disambiguation pages/lists

    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
    çī¹æ®ĬçļĦ
    -0.28
    Ä±ÅŁÄ±
    -0.27
     Vu
    -0.24
    类似çļĦ
    -0.24
    çİ°éĩijæµģ
    -0.24
     bapt
    -0.24
    pace
    -0.24
    åħ¨åªĴä½ĵ
    -0.23
    éłĨ
    -0.22
    èĢĮ对äºİ
    -0.22
    POSITIVE LOGITS
    ĺ认
    0.25
    ↵  ↵
    0.25
    igor
    0.24
    ↵			↵
    0.24
    åijĬçŁ¥
    0.23
    pg
    0.23
    доÑĢ
    0.23
    åĪ°è¾¾
    0.23
    ↵     ↵
    0.23
    åĨĮ
    0.23
    Activations Density 0.165%

    No Known Activations