© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23176
    Prev
    Next
    INDEX
    Explanations

    cancel or escape

    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
    群çļĦ
    -0.08
    ä¸įè¡°
    -0.07
    è¦ģæł¹æį®
    -0.07
    æŶèĬĤ
    -0.06
     Ded
    -0.06
    欢ä¹IJ
    -0.06
    å¼ĢçĽĺ
    -0.06
    iola
    -0.06
     calcul
    -0.06
    åı¯ä»¥æł¹æį®
    -0.06
    POSITIVE LOGITS
    éĢĢåĩº
    0.10
    渤
    0.09
    .exit
    0.08
    æľ¬åľº
    0.08
    quit
    0.08
    .Exit
    0.08
    .terminate
    0.08
    大æ³ķ
    0.08
    ognitive
    0.08
     exits
    0.08
    Activations Density 0.043%

    No Known Activations