© 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. 108683
    Prev
    Next
    INDEX
    Explanations

    indicating

    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
    ***↵
    -0.26
    ä¸Ĭ线
    -0.26
     geçen
    -0.24
    æĸ¯çī¹
    -0.24
     Ñıн
    -0.24
    çļĩåIJİ
    -0.24
     kitty
    -0.23
    ***↵↵
    -0.23
     Clair
    -0.23
    åIJ¬å¾Ĺ
    -0.23
    POSITIVE LOGITS
     early
    0.29
    æĹ©
    0.28
    pi
    0.27
     clearly
    0.25
     pi
    0.25
    (pi
    0.25
     plausible
    0.25
    DMI
    0.25
    å¦Ĥä½ķåİ»
    0.24
    tır
    0.24
    Activations Density 11.905%

    No Known Activations