© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48804
    Prev
    Next
    INDEX
    Explanations

    corresponds to

    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
    æĹ¢çĦ¶æĺ¯
    -0.07
    atap
    -0.06
    ollection
    -0.06
    ester
    -0.06
    ä¸į说è¯Ŀ
    -0.06
     potensial
    -0.06
     Ferd
    -0.06
    uit
    -0.06
     <<"
    -0.06
    åѦäºĨ
    -0.06
    POSITIVE LOGITS
    åĪļ好
    0.08
    çİĭä¹ĭ
    0.08
     justamente
    0.08
    æŃ£å¥½
    0.07
    lesen
    0.07
    åIJijæĹ¥
    0.07
     ppl
    0.07
    åı«åģļ
    0.07
    称ä¹ĭ为
    0.07
     Galler
    0.07
    Activations Density 0.013%

    No Known Activations