© 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. 21629
    Prev
    Next
    INDEX
    Explanations

    holiday season greetings

    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
    æ¯ķä¸ļåħ¸ç¤¼
    -0.08
    utum
    -0.07
    .daily
    -0.07
    æª
    -0.07
    à¸ĺาร
    -0.07
    课éĹ´
    -0.07
    å¼ĢåѦåħ¸ç¤¼
    -0.07
    anyag
    -0.07
    æŶä¸įæŶ
    -0.07
     Torrent
    -0.07
    POSITIVE LOGITS
    åīįå¤ķ
    0.11
    æĿ¥ä¸´
    0.10
    ãĤĴè¿İ
    0.10
    æĿ¥ä¸´ä¹ĭéĻħ
    0.10
     Eve
    0.09
    åį³å°ĨæĿ¥ä¸´
    0.09
    æľŁéĹ´çļĦ
    0.09
    åį³å°ĨåĪ°æĿ¥
    0.09
    åĪ°æĿ¥
    0.08
    è¿ĩåIJİ
    0.08
    Activations Density 0.229%

    No Known Activations