© 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. 64309
    Prev
    Next
    INDEX
    Explanations

    essential oils, repair skin, cellular agent

    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
    çĽ¸ä¼¼æĸĩçĮ®
    -0.08
    è¦ģä¹Ī
    -0.08
    -scripts
    -0.08
     ÙħØ«ÙĦا
    -0.08
     ums
    -0.08
    yll
    -0.08
    allon
    -0.08
    å°Ķ夫
    -0.08
    -cols
    -0.08
    presa
    -0.08
    POSITIVE LOGITS
    ä¹ĭæľ¬
    0.07
    亦æľī
    0.07
    亦åı¯
    0.06
     act
    0.06
     fuss
    0.06
    çŃīä½ľçĶ¨
    0.06
    æ±İ
    0.06
    åħ¼
    0.06
    ä¸İå°ı
    0.06
    çŀ°
    0.06
    Activations Density 0.002%

    No Known Activations