© 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. 34346
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with numbers and operators

    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
    交æīĢ
    -0.07
    ceg
    -0.07
    .tagName
    -0.07
    æķ¬ç¤¼
    -0.07
    ç±»åĪ«
    -0.07
    UDO
    -0.07
    èħ¹åľ°
    -0.07
    geleg
    -0.07
    æħķ
    -0.07
    æĥ®
    -0.07
    POSITIVE LOGITS
    ç»Ĩå¾®
    0.12
     subtle
    0.10
    å¾®å¦Ļ
    0.10
     slight
    0.10
    å¾®è°ĥ
    0.09
     difference
    0.09
     slightly
    0.09
    轻微çļĦ
    0.09
    就差
    0.09
     subtly
    0.09
    Activations Density 0.037%

    No Known Activations