© 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. 30049
    Prev
    Next
    INDEX
    Explanations

    500åĨĨ

    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
    erte
    -0.09
    اتÙĩ
    -0.08
    สà¸ģ
    -0.08
    ì§ĢëıĦ
    -0.08
    æĪªæŃ¢çĽ®åīį
    -0.08
    çļĦä¸ĢåĪĩéĥ½
    -0.08
    ryw
    -0.08
    oins
    -0.08
    ugg
    -0.07
    äºĨ好ä¹ħ
    -0.07
    POSITIVE LOGITS
    çļĦ
    0.08
    å°ıæŶ
    0.07
    æĸ¹éĿ¢çļĦ
    0.07
    å¿ĥåĬ¨
    0.07
    çĵ
    0.06
    ollah
    0.06
    į
    0.06
     Cama
    0.06
    人次
    0.06
    åĴĮå°ļ
    0.06
    Activations Density 0.019%

    No Known Activations