© 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. 2110
    Prev
    Next
    INDEX
    Explanations

    parentheses and mathematical expressions

    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
    溪éķĩ
    -0.07
    ops
    -0.07
    æѦ
    -0.06
    éĶ¦
    -0.06
    ones
    -0.06
    kans
    -0.06
    à¹ĥ
    -0.06
    -0.05
    çIJ¦
    -0.05
    atre
    -0.05
    POSITIVE LOGITS
    anity
    0.09
    rus
    0.08
    åįĩåĪĿ
    0.08
    ométr
    0.07
     Blasio
    0.07
    hada
    0.07
    æī«æııä¸ĭæĸ¹äºĮç»´çłģ
    0.07
    alay
    0.07
    èŀŁ
    0.07
    vera
    0.07
    Activations Density 0.003%

    No Known Activations