© 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. 63116
    Prev
    Next
    INDEX
    Explanations

    copyright and license information

    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
    .wh
    -0.07
     tightly
    -0.06
     te
    -0.06
     parah
    -0.06
     specifically
    -0.06
    еÑģпе
    -0.06
    -chan
    -0.06
    ä¸įä¸Ģå®ļ
    -0.06
    æīĵçģ«
    -0.06
     Te
    -0.06
    POSITIVE LOGITS
     correctness
    0.09
     Correct
    0.08
    correct
    0.08
     correct
    0.08
    itele
    0.08
     Validates
    0.07
    éªĮè¯ģ
    0.07
    æĺ¯æŃ£ç¡®çļĦ
    0.07
    Correct
    0.07
    éĥ½å¾ĹåĪ°äºĨ
    0.07
    Activations Density 0.001%

    No Known Activations