© 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. 25813
    Prev
    Next
    INDEX
    Explanations

    dialogue turn start

    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
    çŁ£
    -0.08
    æľīåħ³äºĭ项
    -0.07
    ollow
    -0.06
     yet
    -0.06
     reportedly
    -0.06
    该
    -0.06
    éļ¾ä¸įæĪIJ
    -0.06
    _dll
    -0.06
    plode
    -0.06
     ÑıкобÑĭ
    -0.06
    POSITIVE LOGITS
    æľºèĬ¯
    0.08
    éĬĺ
    0.07
    âĢ¦I
    0.07
    åĽ¢éĺŁç²¾ç¥ŀ
    0.07
    kost
    0.07
    аÑģа
    0.07
    æľ¬èģĮ
    0.07
    :host
    0.07
    hazi
    0.07
    _launcher
    0.07
    Activations Density 0.138%

    No Known Activations