© 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. 140828
    Prev
    Next
    INDEX
    Explanations

    your

    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
    æĸ¹éĿ¢çļĦ
    -0.27
     bowls
    -0.27
    åĸĿéħĴ
    -0.26
    çĶ¨æīĭ
    -0.25
    athy
    -0.24
    æķijåij½
    -0.24
    ä¹īåĬ¡
    -0.24
    iche
    -0.24
    plusplus
    -0.24
    ç°¿
    -0.24
    POSITIVE LOGITS
    ç´ł
    0.28
    è¸ıä¸Ĭ
    0.26
    大家åĪĨ享
    0.25
    LAG
    0.25
    帷
    0.25
    ONENT
    0.24
    æľĪä¸Ń
    0.24
    åīĶ
    0.24
     callers
    0.24
     Wagner
    0.23
    Activations Density 2.444%

    No Known Activations