© 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. 20-TRANSCODER-HP
    7. 142617
    Prev
    Next
    INDEX
    Explanations

    general

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åĪ°åľº
    -0.32
    ä¸Ģå¹´ä¸Ģ度
    -0.26
     again
    -0.25
    æĹłç¼ĺ
    -0.24
    çļĦåĪ°æĿ¥
    -0.24
     downhill
    -0.24
    ellation
    -0.24
    again
    -0.24
    Ģìŀ¥
    -0.24
    <?=
    -0.24
    POSITIVE LOGITS
     amongst
    0.26
    dent
    0.26
    arent
    0.25
    porter
    0.24
     [|
    0.24
    Vk
    0.24
    æķ°çĽ®
    0.23
    зд
    0.23
     DEM
    0.23
    oya
    0.23
    Activations Density 16.860%

    No Known Activations