© 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. 64386
    Prev
    Next
    INDEX
    Explanations

    code snippets and non-english 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
    ä¸įè¦ģå¿ĺè®°
    -0.07
    ayah
    -0.07
    ipse
    -0.07
    othi
    -0.07
    ypy
    -0.07
    ä½Ļ次
    -0.07
    使åĬ²
    -0.07
    ุà¸ģ
    -0.07
    oks
    -0.07
     virtu
    -0.07
    POSITIVE LOGITS
     presumably
    0.07
    à¤Ĥद
    0.07
    ta
    0.07
    æ¼Ķ
    0.07
    è¶ĭåIJij
    0.07
    åľ
    0.07
    ä¼°è¨Ī
    0.06
    ··
    0.06
    ç»ıéĶĢ
    0.06
    ause
    0.06
    Activations Density 0.014%

    No Known Activations