© 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. 24445
    Prev
    Next
    INDEX
    Explanations

    charge and payment

    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
    ylon
    -0.07
    æĺ¥æ±Ł
    -0.07
    ORB
    -0.07
    à¸Ńยà¹Īาà¸ĩà¹Ħมà¹Īà¸ĸูà¸ģà¸ķà¹īà¸Ńà¸ĩ
    -0.06
    éĢļè¿ĩè¿Ļ个
    -0.06
    è¯ī被åijĬ
    -0.06
    zit
    -0.06
    ừng
    -0.06
    éĢļè¿ĩç½ij绾
    -0.06
     hopefully
    -0.06
    POSITIVE LOGITS
    æīĢ以å½ĵ
    0.12
    ä¸ĢèĪ¬æĥħåĨµä¸ĭ
    0.11
    æīĢ以对äºİ
    0.11
     always
    0.11
    ä½ķæŶ
    0.11
    ä»Ģä¹ĪæŶåĢĻ
    0.11
    åıĸåĨ³äºİ
    0.11
     regardless
    0.11
    åıªæľīåľ¨
    0.11
    Regardless
    0.11
    Activations Density 0.021%

    No Known Activations