© 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. 29440
    Prev
    Next
    INDEX
    Explanations

    section headers

    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
    uncia
    -0.09
    ãģªãģı
    -0.09
     Reinh
    -0.08
    ulte
    -0.08
    ilst
    -0.08
    à§įড
    -0.08
    ão
    -0.08
    áŁĭ
    -0.08
    ´
    -0.08
    åĨħ容æıIJä¾Ľæĸ¹
    -0.08
    POSITIVE LOGITS
     ê°ĻìĿ´
    0.07
     ÐŁÑĢим
    0.07
    e
    0.07
    èģĶç³»æĪij
    0.07
    gi
    0.07
     lắm
    0.06
    æī«ä¸Ģæī«
    0.06
     proven
    0.06
    typ
    0.06
    åŃIJ女çļĦ
    0.06
    Activations Density 0.037%

    No Known Activations