© 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. 12164
    Prev
    Next
    INDEX
    Explanations

    distinction between 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
    éħ£
    -0.07
    epas
    -0.07
    æ²ĥæĸ¯
    -0.07
    åIJĦè¡ĮåIJĦ
    -0.06
     involved
    -0.06
    _helpers
    -0.06
    errat
    -0.06
    çĮ
    -0.06
    åŀĴ
    -0.06
    idle
    -0.06
    POSITIVE LOGITS
     distinction
    0.11
     distinctions
    0.10
     synonymous
    0.10
     naming
    0.10
     spelling
    0.10
     renaming
    0.09
    omencl
    0.09
    åIJį称
    0.09
     interchangeable
    0.09
    çļĦåĮºåĪ«
    0.09
    Activations Density 0.085%

    No Known Activations