© 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. 12988
    Prev
    Next
    INDEX
    Explanations

    mathematical inequalities or equalities

    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
    acruz
    -0.07
     cenu
    -0.07
    שת
    -0.07
    çŁ¯
    -0.07
    uted
    -0.07
    жек
    -0.06
    ["_
    -0.06
    å°Ķæĸ¯
    -0.06
    æħķå°¼
    -0.06
     -
    -0.06
    POSITIVE LOGITS
     inequalities
    0.09
    ä¸įçŃī
    0.09
     equality
    0.09
     inequality
    0.09
    equality
    0.08
    æĿ¡ä»¶æĺ¯
    0.08
    åīįæıIJæĺ¯
    0.08
     satisfying
    0.08
    ifel
    0.07
     satisfies
    0.07
    Activations Density 0.038%

    No Known Activations