© 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. 27698
    Prev
    Next
    INDEX
    Explanations

    granted patents

    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
    addon
    -0.07
    ัà¸ķ
    -0.07
    è¿ŀäºij
    -0.07
    lager
    -0.07
    بÙĤ
    -0.07
    hee
    -0.07
    éħįç½®çļĦ
    -0.06
    天ä¹ĭ
    -0.06
     EVE
    -0.06
    åįĪé¥Ń
    -0.06
    POSITIVE LOGITS
     Granted
    0.08
    å±ķå¼Ģåħ¨éĥ¨
    0.08
     awarded
    0.07
    Granted
    0.07
    ément
    0.07
    æķĪåĬĽçļĦ
    0.07
    å¾IJæŁIJ
    0.07
    被æİĪäºĪ
    0.07
    åħ¸
    0.07
    ä»Ģä¹ĪæĥħåĨµ
    0.07
    Activations Density 0.140%

    No Known Activations