© 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. 17512
    Prev
    Next
    INDEX
    Explanations

    chemical compound suffixes

    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
    rej
    -0.08
    åĮĸåĴĮ
    -0.08
    æ¼ı
    -0.07
    è¿ĶåĽŀåĪĹ表
    -0.07
    æī¹åĩĨçļĦé¡¹çĽ®
    -0.07
    awat
    -0.07
    çĬ
    -0.07
    rhein
    -0.07
    akh
    -0.07
    为éĩį
    -0.06
    POSITIVE LOGITS
    åŁºç¡Ģä¸Ĭ
    0.11
    æľ¬èº«çļĦ
    0.10
     originally
    0.09
    æľ¬èº«
    0.09
    æľ¬èº«å°±
    0.09
    çļĦåŁºç¡Ģä¸Ĭ
    0.09
    åľ¨æŃ¤åŁºç¡Ģä¸Ĭ
    0.08
     itself
    0.08
     baseline
    0.08
    æľ¬æĿ¥å°±
    0.08
    Activations Density 0.073%

    No Known Activations