© 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. 32150
    Prev
    Next
    INDEX
    Explanations

    @since version or @memberOf _

    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
    á»ijc
    -0.07
    OTOR
    -0.07
    æĿŀ
    -0.07
    ë¹ĦìķĦ
    -0.07
    [color
    -0.06
    Associate
    -0.06
    æĮij
    -0.06
    à®±à¯įப
    -0.06
    大éŨ
    -0.06
    rowse
    -0.06
    POSITIVE LOGITS
    åľ¨å¿ħ
    0.07
     apro
    0.07
    èĥ§
    0.07
    łĢ
    0.07
    好åѦçĶŁ
    0.06
    絶
    0.06
    +:
    0.06
    Ĺı
    0.06
     #:
    0.06
    æ¯ıä¸Ģ个åѦçĶŁ
    0.06
    Activations Density 0.031%

    No Known Activations