© 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. 46020
    Prev
    Next
    INDEX
    Explanations

    maximal, maximal, maximizing, sequences, subsets

    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
     asymmetric
    -0.08
    è¿Ļ两ä½į
    -0.08
    æĹ©çŁ¥éģĵ
    -0.08
    è¿Ļ两款
    -0.07
    ä¸į对称
    -0.07
     asym
    -0.07
    磺
    -0.06
    ç¤
    -0.06
    ä¸īæĿ¿
    -0.06
     Bil
    -0.06
    POSITIVE LOGITS
    çļĦæľĢ大
    0.10
     maximal
    0.09
    æľĢ大
    0.09
     maxSize
    0.09
    æľĢå¤ļ
    0.09
    æľĢ大åĮĸ
    0.08
    åŃĺæĶ¾
    0.08
     maximizing
    0.08
    lacht
    0.08
    subset
    0.08
    Activations Density 0.009%

    No Known Activations