© 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. 23193
    Prev
    Next
    INDEX
    Explanations

    verb followed by action or state

    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
    使èĩªå·±çļĦ
    -0.08
    åĩ¡äºĭ
    -0.07
    æݧãģĪ
    -0.07
    uspended
    -0.07
     Earn
    -0.07
    é¥®é£Łä¸Ĭ
    -0.06
     renunci
    -0.06
    bt
    -0.06
     enunci
    -0.06
    é¢Ħ约æĮĤåı·
    -0.06
    POSITIVE LOGITS
    å¤ĦçIJĨåIJİ
    0.12
    çĶ¨éĢĶ
    0.09
    妥åĸĦ
    0.09
    æĬĬå®ĥ们
    0.09
    åŃĺæĶ¾åľ¨
    0.09
    åŃĺæĶ¾
    0.09
    对åħ¶è¿Ľè¡Į
    0.09
    å¤ĦçIJĨæĸ¹å¼ı
    0.09
    å¤ĦçIJĨåĴĮ
    0.09
    ä¿Ŀ管
    0.08
    Activations Density 0.387%

    No Known Activations