© 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. 25318
    Prev
    Next
    INDEX
    Explanations

    foreign language characters

    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
    :id
    -0.07
    Singleton
    -0.06
    Inlining
    -0.06
    Ñģк
    -0.06
    mol
    -0.06
    =start
    -0.06
    åįİåºľ
    -0.06
    ::__
    -0.06
    çĶŁ
    -0.06
    dtype
    -0.06
    POSITIVE LOGITS
    ohan
    0.08
    ä¹ĭ乡
    0.08
    åıªæĺ¯ä¸Ģç§į
    0.07
     âĵĴ
    0.07
    _cre
    0.07
    коÑģ
    0.07
    鼨çļĦ
    0.07
    äºĶèĬ±åħ«
    0.07
    ä¹±æīĶ
    0.07
    æ¹¾
    0.07
    Activations Density 0.014%

    No Known Activations