© 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. 50874
    Prev
    Next
    INDEX
    Explanations

    tool

    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
    ÃŃr
    -0.07
    abora
    -0.07
    ykl
    -0.07
    xAB
    -0.06
    xDE
    -0.06
    å¦Ĵ
    -0.06
    entrale
    -0.06
    éķ¿æľŁä»¥æĿ¥
    -0.06
    åĩ¡äºĭ
    -0.06
    iebe
    -0.06
    POSITIVE LOGITS
    ($(
    0.07
    éľ²éĿ¢
    0.07
     ../../../
    0.07
    åIJ«éĩijéĩı
    0.07
    æĽ´ä½ķåĨµ
    0.07
    RLF
    0.06
    è§ģ人
    0.06
    Ref
    0.06
    æĹłæķĮ
    0.06
    رÙĪÙĬ
    0.06
    Activations Density 0.097%

    No Known Activations