© 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. 55489
    Prev
    Next
    INDEX
    Explanations

    method call syntax

    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
    西æŀĹ
    -0.08
    ìį¨
    -0.08
    ÙĪرد
    -0.07
    änn
    -0.07
    å·¥ä½ľåľ¨
    -0.07
    apol
    -0.07
    ord
    -0.07
    acer
    -0.07
    olis
    -0.07
    ä»ĭçŁ³
    -0.07
    POSITIVE LOGITS
    ç®Ģ称
    0.10
    ä¸ĭ称
    0.07
    以ä¸ĭç®Ģ称
    0.07
    дови
    0.07
    簡稱
    0.06
     upkeep
    0.06
     eskort
    0.06
    ç§ijåijĺ
    0.06
    æŀģ管
    0.06
    _Msk
    0.06
    Activations Density 2.483%

    No Known Activations