© 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. 39364
    Prev
    Next
    INDEX
    Explanations

    section headings or document goals

    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
     spoken
    -0.06
    æĤ£ä¸Ĭ
    -0.06
    è¿ĺ好
    -0.06
    ×ĵ×Ķ
    -0.06
    Ùģت
    -0.06
    enco
    -0.06
    tais
    -0.06
    enal
    -0.06
    å¾Ī好å¥ĩ
    -0.06
    åľ¨è¿Ļæł·çļĦ
    -0.06
    POSITIVE LOGITS
    ign
    0.08
    åĪ°å¤´
    0.08
     Rogers
    0.07
    ibel
    0.07
    cala
    0.07
    anteed
    0.07
    Tel
    0.07
     RUR
    0.07
    æ°¸è¿ľæĺ¯
    0.07
    URG
    0.07
    Activations Density 0.001%

    No Known Activations