© 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. 28995
    Prev
    Next
    INDEX
    Explanations

    measured variables

    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
    áĥ¥
    -0.06
     nearest
    -0.06
    Utils
    -0.06
    èĢ³
    -0.06
     cat
    -0.06
    æŃ¤æ¬¡
    -0.06
    ÃŃssima
    -0.06
    nearest
    -0.06
    ÃŃssimo
    -0.06
     Wyn
    -0.06
    POSITIVE LOGITS
    ä¸Ģå®ļçļĦ
    0.09
    enor
    0.08
     independ
    0.08
    ept
    0.08
    -Clause
    0.08
    åľ¨ä¸Ģå®ļ
    0.08
    è°ĥæķ´å¥½
    0.08
    auan
    0.07
    åįĩåĪĿ
    0.07
    çļĦåīįæıIJä¸ĭ
    0.07
    Activations Density 0.018%

    No Known Activations