© 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. 33996
    Prev
    Next
    INDEX
    Explanations

    year or date markers

    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
    o
    -0.11
    çļĦ
    -0.10
    о
    -0.09
    åĴĮ
    -0.09
    æĸ°åĬłåĿ¡
    -0.09
    а
    -0.08
    ÏĤ
    -0.08
    Ø©
    -0.08
    ed
    -0.08
    ов
    -0.08
    POSITIVE LOGITS
    å·¦åı³çļĦ
    0.08
    zinho
    0.08
    ien
    0.08
    次çļĦ
    0.08
    ãģ¾ãģ§ãģ«
    0.07
    çļĦ人éĻħåħ³ç³»
    0.07
    ÑĤÑĮÑı
    0.07
    åıĬ以ä¸ĬçļĦ
    0.07
    /'
    0.07
    ãģ°ãģĭãĤĬ
    0.07
    Activations Density 0.004%

    No Known Activations