© 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. 15258
    Prev
    Next
    INDEX
    Explanations

    commonly used phrases

    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
    å¦ĤåĪĿ
    -0.07
    ëĿ¼ëıĦ
    -0.07
    麾
    -0.07
    MAND
    -0.07
    æ¥ļ
    -0.06
    ×ķש
    -0.06
     height
    -0.06
    ением
    -0.06
    esa
    -0.06
    ä¸įèĻļ
    -0.06
    POSITIVE LOGITS
    éĢļ常
    0.11
     suele
    0.11
     suelen
    0.10
     commonly
    0.09
    éĢļ常æĺ¯
    0.09
     typically
    0.09
     обÑĭÑĩно
    0.09
    常è§ģçļĦ
    0.09
     biasanya
    0.09
    éĢļ常ä¼ļ
    0.09
    Activations Density 0.246%

    No Known Activations