© 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. 61422
    Prev
    Next
    INDEX
    Explanations

    numeral designation

    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
     lux
    -0.07
    lux
    -0.07
    段
    -0.07
    第äºĮ段
    -0.07
     outr
    -0.07
    æīĭä¸ĬçļĦ
    -0.06
    emann
    -0.06
    第ä¸īèĢħ
    -0.06
    neau
    -0.06
    å¤ĦçIJĨæĸ¹æ³ķ
    -0.06
    POSITIVE LOGITS
    omber
    0.07
    antos
    0.07
    æ¼ĵ
    0.07
    èĵī
    0.07
    ëĿ¼
    0.07
    该åĨħ容
    0.07
    å¾·ç½Ĺ
    0.07
    ä¸ĢèĪ¬èĢĮè¨Ģ
    0.07
    abeled
    0.06
     consists
    0.06
    Activations Density 0.088%

    No Known Activations