© 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. 51774
    Prev
    Next
    INDEX
    Explanations

    involved in calculation

    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
    ä¸ĵ家åѦèĢħ
    -0.08
     streng
    -0.08
    Ø®ÙĨ
    -0.08
    å®Ļ
    -0.08
    own
    -0.07
    大ç¥ŀ
    -0.07
    ersh
    -0.07
     ")"
    -0.07
    ader
    -0.07
    è¦ĥ
    -0.07
    POSITIVE LOGITS
     calculation
    0.08
     calculates
    0.08
    æĥħå¢ĥ
    0.07
    年建
    0.07
    计ç®Ĺåĩº
    0.07
     solved
    0.07
    计ç®Ĺ
    0.07
     calculating
    0.07
    çŃĶæ¡Īæĺ¯
    0.06
    äºĭ件çļĦ
    0.06
    Activations Density 0.003%

    No Known Activations