© 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. 29796
    Prev
    Next
    INDEX
    Explanations

    proper nouns and technical terms

    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
    æĽ´å¤ļ精彩åĨħ容
    -0.09
    formatter
    -0.07
    grounds
    -0.07
    å°½æľī
    -0.07
    iesz
    -0.07
    gar
    -0.06
    icules
    -0.06
    lickr
    -0.06
     porque
    -0.06
     grounds
    -0.06
    POSITIVE LOGITS
    åľ¨è¿Ļæĸ¹éĿ¢
    0.09
    以æŃ¤ä¸º
    0.08
    å°±æѤ
    0.08
     بذÙĦÙĥ
    0.08
     accordingly
    0.08
    ä»İè¿Ļ个
    0.08
     nisso
    0.08
    úm
    0.07
    oyo
    0.07
    åľ¨è¿Ļç§įæĥħåĨµä¸ĭ
    0.07
    Activations Density 0.002%

    No Known Activations