© 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. 45646
    Prev
    Next
    INDEX
    Explanations

    prime factors

    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
    çİĩä½İ
    -0.08
    çİĩè¾¾åĪ°
    -0.07
    幽幽
    -0.07
    å¸Ń
    -0.07
    _HANDLE
    -0.07
    çİĩ为
    -0.07
    czyk
    -0.07
    æİ¥ä¸ĭæĿ¥çļĦ
    -0.07
    被ç½ļ
    -0.07
     декл
    -0.07
    POSITIVE LOGITS
    ohn
    0.08
    ERO
    0.08
    æ¯ıç»Ħ
    0.07
    æķ´
    0.07
    -binary
    0.07
    essler
    0.07
    æŀŃ
    0.07
    æĹłæĤĶ
    0.06
    没äºĭ
    0.06
     pounded
    0.06
    Activations Density 0.055%

    No Known Activations