© 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. 61757
    Prev
    Next
    INDEX
    Explanations

    static variable or constant declaration

    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
     diras
    -0.09
    åį³åĪ°
    -0.08
    RootElement
    -0.08
    izoph
    -0.08
     nyn
    -0.08
    åĪģ
    -0.07
    å°±ä¸Ģå®ļè¦ģ
    -0.07
    łĢ
    -0.07
    arien
    -0.07
    arina
    -0.07
    POSITIVE LOGITS
    æĽ´çĶŁ
    0.07
     noexcept
    0.07
    继æī¿
    0.07
    ph
    0.07
    çĽ¸ä¼¼æĸĩçĮ®
    0.06
    ç¬ĭ
    0.06
    ottaa
    0.06
    è¿ĩæŶ
    0.06
     getattr
    0.06
    ä¸ĢæŶ
    0.06
    Activations Density 0.134%

    No Known Activations