© 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. 23302
    Prev
    Next
    INDEX
    Explanations

    special characters and mathematical notation

    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
    enom
    -0.07
    adak
    -0.06
    ================================================================================
    -0.06
    éĥ½æĺ¯çĶ¨
    -0.06
    cratch
    -0.06
    éĥ½æĺ¯åı¯ä»¥
    -0.06
    мей
    -0.06
    çĻĤ
    -0.06
    нам
    -0.06
    å¬Į
    -0.06
    POSITIVE LOGITS
    å¼ģ
    0.07
    çĤľ
    0.07
     pháºŃn
    0.07
    为ä¸Ģä½ĵçļĦ
    0.07
    éĶĻ误çļĦæĺ¯
    0.07
    bah
    0.07
     pula
    0.07
     ë¶Ī리ëĬĶ
    0.06
    jú
    0.06
    æĿ¥ä¸ºå¤§å®¶
    0.06
    Activations Density 1.015%

    No Known Activations