© 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. 25297
    Prev
    Next
    INDEX
    Explanations

    global or worldwide scope

    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
    ë°©
    -0.07
    YW
    -0.07
    bem
    -0.06
    akis
    -0.06
    ТÐĴ
    -0.06
    ç»ıèIJ¥è®¸åı¯è¯ģ
    -0.06
    èĦĬ
    -0.06
    alap
    -0.06
    anga
    -0.06
    akil
    -0.06
    POSITIVE LOGITS
     globally
    0.13
    éĴĪ对
    0.12
     worldwide
    0.11
    æĺ¯éĴĪ对
    0.10
    åľ¨æ¯ı个
    0.10
    global
    0.10
     باÙĦÙĨسبة
    0.10
    éĩĿå°į
    0.10
    对äºİ
    0.10
    overall
    0.10
    Activations Density 0.555%

    No Known Activations