© 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. 23066
    Prev
    Next
    INDEX
    Explanations

    CR

    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
    åľ¨æĹ¥å¸¸
    -0.09
    èİ«åıĬ
    -0.08
    åľ¨éĺħ读
    -0.07
    ÙĨاÙĨ
    -0.07
    ruik
    -0.07
    åľ¨çĶŁæ´»
    -0.07
    orme
    -0.07
    orm
    -0.07
    ازÙĩ
    -0.07
    tro
    -0.06
    POSITIVE LOGITS
    ä¸Ńéĩij
    0.07
    ä¸Ĭ空
    0.07
    çªĿ
    0.07
     Reihen
    0.07
    arge
    0.07
     munch
    0.06
     í
    0.06
    ises
    0.06
    losing
    0.06
    æ·ij
    0.06
    Activations Density 0.001%

    No Known Activations