© 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. 11593
    Prev
    Next
    INDEX
    Explanations

    mathematical and asian 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
    è´¨éĩıæĬĢæľ¯çĽijçĿ£
    -0.08
    θα
    -0.07
    éĽ¨éľ²
    -0.07
    æĻ®æ£®
    -0.07
    ä¸Ģè¿Ľ
    -0.07
    culated
    -0.07
    å¼ıä¸Ń
    -0.07
    ä¹İåħ¶
    -0.07
    ij¸
    -0.07
    éľ
    -0.06
    POSITIVE LOGITS
    ืà¸Ńà¸ĩ
    0.08
    大éĩij
    0.07
    lera
    0.07
    äºĮåįģå¹´
    0.07
    ä¸īæĹ¥
    0.07
    èªī为
    0.07
    -results
    0.06
    åħ«å¤§
    0.06
    à¹Īะ
    0.06
    _objects
    0.06
    Activations Density 0.009%

    No Known Activations