© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20236
    Prev
    Next
    INDEX
    Explanations

    audio-books, ebooks, chips, Rectangle, sulfur, Hampshire

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸Ģè§ģ
    -0.07
     lower
    -0.07
    airo
    -0.06
    å°±è¿Ļä¹Ī
    -0.06
    æıIJä¾ĽåIJĦç§į
    -0.06
    omic
    -0.06
    itable
    -0.06
    æŃ£æľ¬
    -0.06
    erness
    -0.06
    交æµģåŃ¦ä¹ł
    -0.06
    POSITIVE LOGITS
    ãģĵãģ¡ãĤīãĤĤ
    0.08
    hj
    0.08
    æĭĽ
    0.08
    .pool
    0.08
    $$$$
    0.07
     ebenfalls
    0.07
     ikut
    0.07
     ÄijÃł
    0.07
    ãĥ¼ãĤ¸ãĥ¥
    0.07
    qv
    0.07
    Activations Density 0.106%

    No Known Activations