© 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. 51697
    Prev
    Next
    INDEX
    Explanations

    synonyms or replacements

    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
    claimed
    -0.08
    drs
    -0.08
    assen
    -0.08
    声称
    -0.07
    å®īæİĴ好
    -0.07
     claimed
    -0.07
    æĢ»ä½ĵä¸Ĭ
    -0.07
    åİķ
    -0.07
    lus
    -0.07
    åı¯åĪ©çĶ¨
    -0.07
    POSITIVE LOGITS
    ç©ºæł¼
    0.09
    填空
    0.08
     synonyms
    0.08
     replacements
    0.08
     nouns
    0.08
     yerine
    0.08
     interchangeable
    0.08
    è¿ijä¹īè¯į
    0.08
    å¡«åħ¥
    0.08
     fill
    0.08
    Activations Density 0.003%

    No Known Activations