© 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. 64644
    Prev
    Next
    INDEX
    Explanations

    Formal writing/events

    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
    èł¹
    -0.26
    è¶ĬæĿ¥è¶Ĭé«ĺ
    -0.25
     fick
    -0.25
     trữ
    -0.25
     wink
    -0.25
    èĵ
    -0.24
    _dispatcher
    -0.24
     indexer
    -0.24
     Deadly
    -0.24
    /lic
    -0.24
    POSITIVE LOGITS
    onte
    0.29
    æıIJ
    0.28
     su
    0.27
    ä¸Ģè´¯
    0.27
     Cour
    0.26
    说å®ŀ
    0.26
    adx
    0.24
    ä»ĭç»į
    0.24
     Judgment
    0.24
    è¿«
    0.23
    Activations Density 10.107%

    No Known Activations