© 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. 49042
    Prev
    Next
    INDEX
    Explanations

    equivalency factor dose risk index

    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
    ยัà¸Ļ
    -0.08
    翱
    -0.07
    æ¦ķ
    -0.07
    Õ»
    -0.07
    à¸ķิà¸ģ
    -0.07
    åı²å¯Ĩæĸ¯
    -0.07
    ç«ŀäºīé£İéĻ©
    -0.07
    åĨħå¤ĸ
    -0.07
    解åĨ³éĹ®é¢ĺçļĦ
    -0.07
    ØŃÙĦ
    -0.07
    POSITIVE LOGITS
     weighted
    0.10
    åĬłæĿĥ
    0.10
    weighted
    0.10
     weighting
    0.10
    -weight
    0.09
     weights
    0.08
    æĺ¼
    0.08
     standardized
    0.07
    Weight
    0.07
    ä¸Ģ票
    0.07
    Activations Density 0.022%

    No Known Activations