© 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. 31976
    Prev
    Next
    INDEX
    Explanations

    yes / certainly

    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
    ä¹Łä½¿
    -0.08
    æľīä¸ĢèĤ¡
    -0.07
    ijn
    -0.07
    lush
    -0.07
    _figure
    -0.07
    igure
    -0.07
    åľ¨åį³
    -0.07
    æĿĥ
    -0.07
    ÑĮÑİ
    -0.06
    ä¾¥
    -0.06
    POSITIVE LOGITS
    yes
    0.10
     yes
    0.09
     Yes
    0.08
    確ãģĭãģ«
    0.08
    Yes
    0.08
    ç¡®å®ŀ
    0.08
    èĩ³äºİ
    0.08
    _yes
    0.08
    åIJ¦
    0.08
     certainly
    0.07
    Activations Density 0.118%

    No Known Activations