© 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. 13418
    Prev
    Next
    INDEX
    Explanations

    calculate a numeric value

    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
    epass
    -0.09
    åįķä½ĵ
    -0.08
    ATTR
    -0.08
    -pt
    -0.08
    ĮĢ
    -0.08
    andalone
    -0.08
    -zA
    -0.08
    ä¸Ģèµ·åľ¨
    -0.08
    æľªç»ı许åı¯
    -0.08
    cloak
    -0.08
    POSITIVE LOGITS
     integer
    0.08
    éĹª
    0.07
     bin
    0.07
    ç¡®å®ļ
    0.07
     determining
    0.07
     Determin
    0.07
     whenever
    0.07
     determin
    0.07
     ordinal
    0.07
     subsequ
    0.07
    Activations Density 0.012%

    No Known Activations