© 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. 43713
    Prev
    Next
    INDEX
    Explanations

    start by saying that

    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
    коми
    -0.08
    ç¨įæľī
    -0.08
    ÙĪارÙĩ
    -0.08
    ׳×Ļ×ķת
    -0.07
    å®ļè¦ģ
    -0.07
    urch
    -0.07
     Ú©ÙħÛĮ
    -0.07
    è¿ĺåı¯èĥ½
    -0.07
    òi
    -0.07
    øs
    -0.07
    POSITIVE LOGITS
     nhé
    0.08
     bahwa
    0.08
    è¿Ļæĺ¯ä¸Ģç§į
    0.07
    ä¸įæĺ¯åĽłä¸º
    0.07
    odule
    0.07
    ãģĤãģı
    0.07
     specifics
    0.07
     perché
    0.07
    ä½ľçĶ¨åĴĮ
    0.07
     stringify
    0.06
    Activations Density 0.008%

    No Known Activations