© 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. 11231
    Prev
    Next
    INDEX
    Explanations

    answer in terms of

    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
    vik
    -0.07
    liv
    -0.07
    ucker
    -0.07
    zec
    -0.07
    å°±æĽ´
    -0.07
    amic
    -0.07
    å®ĥå°±æĺ¯
    -0.07
    æĽ´ä¸įæĺ¯
    -0.07
    ä»ĸå°±æĺ¯
    -0.07
    asics
    -0.07
    POSITIVE LOGITS
    eru
    0.07
    дии
    0.07
    ç¦ı
    0.06
    ä¼ijæĹ¥
    0.06
    (Duration
    0.06
    æľī家
    0.06
    天å¿ĥ
    0.06
    æīĢæĢĿ
    0.06
    çĶĺå¿ĥ
    0.06
     postings
    0.06
    Activations Density 0.020%

    No Known Activations