© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17870
    Prev
    Next
    INDEX
    Explanations

    filed, deposited, from

    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
    åīįæĿ¥
    -0.07
    çĽĺé¾Ļ
    -0.07
    åľ¨æŃ¤åŁºç¡Ģä¸Ĭ
    -0.07
     Ø®ÙĦاÙĦÙĩا
    -0.07
    ordon
    -0.07
    åľ¨è¿Ļ段æŶéĹ´
    -0.07
    åľ¨æѤ
    -0.07
    .iOS
    -0.07
    Parcel
    -0.07
    åľ¨è¿Ļç§įæĥħåĨµä¸ĭ
    -0.07
    POSITIVE LOGITS
    æīĢåľ¨çļĦ
    0.13
    åĨĻåľ¨
    0.13
    åŃĺåľ¨äºİ
    0.13
    åıijè¡¨åľ¨
    0.13
    åħĪåľ¨
    0.12
    åŃĺåĤ¨åľ¨
    0.12
    继ç»Ńåľ¨
    0.12
    ä¿ĿåŃĺåľ¨
    0.12
    åŃĺæĶ¾åľ¨
    0.11
    à¹Ħวà¹īà¹ĥà¸Ļ
    0.11
    Activations Density 1.498%

    No Known Activations