© 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. 22146
    Prev
    Next
    INDEX
    Explanations

    lists punctuation

    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
    =>"
    -0.08
     wiÄĻc
    -0.08
    å°ļæľī
    -0.07
    olume
    -0.07
    ÑĢенд
    -0.07
    å¾·åįİ
    -0.07
    ocument
    -0.07
     Ristor
    -0.07
     Mediterr
    -0.07
    UIViewController
    -0.07
    POSITIVE LOGITS
    ix
    0.08
    æľĢéĩįè¦ģçļĦæĺ¯
    0.07
    æĽ´éĩįè¦ģçļĦæĺ¯
    0.07
    ãģķãģ¦
    0.07
    zio
    0.07
    éĴĪ对
    0.06
    软çļĦ
    0.06
    HL
    0.06
    aca
    0.06
    æĽ´ä¸įæĺ¯
    0.06
    Activations Density 0.141%

    No Known Activations