© 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. 24005
    Prev
    Next
    INDEX
    Explanations

    CH.sub.2, CHR, CH

    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
    zer
    -0.07
    endis
    -0.07
    หม
    -0.07
    дÑĥк
    -0.07
    weit
    -0.06
    åĴĮè°IJ
    -0.06
     postfix
    -0.06
    庸
    -0.06
    ruk
    -0.06
    สà¹Į
    -0.06
    POSITIVE LOGITS
    elain
    0.09
    åĸľéĹ»
    0.08
    eled
    0.08
    ä¸Ģéĥİ
    0.07
    cho
    0.07
    ино
    0.07
    èĢIJåĬ³
    0.07
    Scheduled
    0.07
    ÄŁÃ¼
    0.07
    icara
    0.07
    Activations Density 0.003%

    No Known Activations