© 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. 31-TRANSCODER-HP
    7. 19721
    Prev
    Next
    INDEX
    Explanations

    code, math

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    å½¹
    -0.32
    instruction
    -0.30
     Instruction
    -0.30
    æĮĩ令
    -0.29
     instruction
    -0.29
     Test
    -0.28
     instructions
    -0.27
    ãĤ¹ãĤ¯
    -0.27
    éĺī
    -0.27
     Grammar
    -0.27
    POSITIVE LOGITS
    èįīåĿª
    0.27
    .viewer
    0.27
    ä¸ĬæĿ¥
    0.26
     smack
    0.25
    endo
    0.25
    ä½ĵèĤ²åľº
    0.25
     sticker
    0.25
    etri
    0.24
    第ä¸ī次
    0.24
    toi
    0.24
    Activations Density 0.117%

    No Known Activations