© 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. 108705
    Prev
    Next
    INDEX
    Explanations

    less, more

    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
    pure
    -0.31
    纯
    -0.27
     pure
    -0.26
     Ach
    -0.26
     Pure
    -0.26
    jit
    -0.25
    ched
    -0.25
     mapDispatchToProps
    -0.25
    affe
    -0.24
     Fre
    -0.24
    POSITIVE LOGITS
    edReader
    0.25
    æļ
    0.25
    æ³ķåĪĻ
    0.25
    å¾Ĺèµ·
    0.25
     Specs
    0.24
    ç§ijåѦéĻ¢
    0.24
    enso
    0.23
    (er
    0.23
    æĺ¯åı¯ä»¥
    0.23
    話ãĤĴ
    0.23
    Activations Density 17.913%

    No Known Activations