© 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. 27-TRANSCODER-HP
    7. 9694
    Prev
    Next
    INDEX
    Explanations

    say "the"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    è¿ĺ好
    -0.28
    agrams
    -0.26
    ltk
    -0.26
    licting
    -0.24
    æľĪåĪĿ
    -0.24
    xDA
    -0.24
    AMY
    -0.23
    ÐĽÐ¬
    -0.23
    xee
    -0.23
    libft
    -0.23
    POSITIVE LOGITS
    æķ´ä¸ª
    0.56
    åħ¨åĽ½
    0.55
     across
    0.50
     entire
    0.49
    åħ¨çľģ
    0.48
    åħ¨å¸Ĥ
    0.48
     globe
    0.47
    åħ¨çIJĥ
    0.47
    åľ¨æķ´ä¸ª
    0.47
    åħ¨åľĭ
    0.46
    Activations Density 0.029%

    No Known Activations