© 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. 38707
    Prev
    Next
    INDEX
    Explanations

    occupational therapy and veterinary medicine

    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
    为èį£
    -0.08
     Alqu
    -0.08
    ä¼ģä¸ļèį£èªī
    -0.08
    ÅĽc
    -0.08
    TemplateName
    -0.08
    URLRequest
    -0.08
    ombok
    -0.07
    ezet
    -0.07
    åı£éŁ³
    -0.07
     cerem
    -0.07
    POSITIVE LOGITS
    æ¦Ĥ论
    0.09
    ä¸ŃåĽ½å®¶
    0.08
    è§ĦåĪĴ设计
    0.07
    çļĦ太éĺ³
    0.06
    åħŃ大
    0.06
    第äºĮçĻ¾
    0.06
    çŁ¥ç½ij
    0.06
    éŀł
    0.06
    设计ä¸İ
    0.06
    ç¦ıçĶ°
    0.06
    Activations Density 0.357%

    No Known Activations