© 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. 29597
    Prev
    Next
    INDEX
    Explanations

    ideal, perfect, universally

    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
    екÑģи
    -0.09
     khá
    -0.09
    为主çļĦ
    -0.09
    ấm
    -0.08
     неодно
    -0.08
     ë¹ĦêµIJìłģ
    -0.08
     maggiormente
    -0.08
    è¾ĥå¤ļ
    -0.08
    ä¸ºå®ľ
    -0.08
     mainly
    -0.08
    POSITIVE LOGITS
     perfect
    0.16
     perfectly
    0.16
    å®Įç¾İçļĦ
    0.15
    å®Įç¾İ
    0.15
     Perfect
    0.15
    çļĦå®Įç¾İ
    0.14
     flawless
    0.14
    perfect
    0.14
    Perfect
    0.13
    æĹłä»»ä½ķ
    0.12
    Activations Density 0.046%

    No Known Activations