© 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. 106845
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
    orks
    -0.27
    ä»·ä½į
    -0.26
    èģĶç³»æĸ¹å¼ı
    -0.25
    _IMPL
    -0.25
    alu
    -0.25
    çī¹åĪ«
    -0.25
     triá»ĥn
    -0.23
     Alo
    -0.23
    对ä»ĺ
    -0.23
     Lid
    -0.23
    POSITIVE LOGITS
    icro
    0.29
    .cleanup
    0.29
    ä¸įåĨįæĺ¯
    0.28
    æħ·æħ¨
    0.27
    rift
    0.26
    èĩªåĬ¨åĮĸ
    0.25
    ãĥ¬ãĥ³
    0.25
    æıIJæĹ©
    0.25
     mounting
    0.23
    è¯ģ书
    0.23
    Activations Density 1.514%

    No Known Activations