© 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. 33165
    Prev
    Next
    INDEX
    Explanations

    synonyms, work, high, skill, admin sections

    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
    resher
    -0.07
    åħ¶ä¸ī
    -0.07
     právÄĽ
    -0.06
     fray
    -0.06
    adic
    -0.06
    并ä¸įæĺ¯
    -0.06
    ''
    -0.06
    为äºĨæĸ¹ä¾¿
    -0.06
    '',
    -0.06
    åŁł
    -0.06
    POSITIVE LOGITS
    åı¯åIJ¦
    0.10
    åı¯è¨Ģ
    0.09
    主ãģª
    0.08
     (%)
    0.08
    åĤĻèĢĥ
    0.08
    åįłåħ¨åĽ½
    0.08
     BEFORE
    0.07
    ajor
    0.07
    æľīæĹł
    0.07
    ç»Ļ人çļĦ
    0.07
    Activations Density 0.005%

    No Known Activations