© 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. 34237
    Prev
    Next
    INDEX
    Explanations

    legal or technical specific terms

    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
    imulator
    -0.09
    äºİä¸Ģ
    -0.08
    cest
    -0.08
     Stich
    -0.07
    å®ĥæĺ¯ä¸Ģç§į
    -0.07
    ERGE
    -0.07
    -ish
    -0.07
    ¸
    -0.07
    моби
    -0.07
    à¹ĥหà¹īà¹Ħà¸Ķà¹ī
    -0.07
    POSITIVE LOGITS
    建置
    0.06
    æĸ°æĹ¶æľŁ
    0.06
    éĻ¤æ¹¿
    0.06
    ද
    0.06
    æįķ
    0.06
    æºIJ
    0.06
    YY
    0.06
    åįı
    0.06
    alt
    0.06
    اÙĩ
    0.06
    Activations Density 0.001%

    No Known Activations