© 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. 58752
    Prev
    Next
    INDEX
    Explanations

    digits and mathematical operations

    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
    ÙĨاÙħÙĩ
    -0.07
    å¸ĪèĮĥåѦéĻ¢
    -0.07
    à¸Ĺัย
    -0.07
     ÑģобÑĸ
    -0.07
    innen
    -0.07
    AndGet
    -0.07
    Interpolator
    -0.06
    esh
    -0.06
    aram
    -0.06
     lowercase
    -0.06
    POSITIVE LOGITS
     consign
    0.07
    olata
    0.07
    iop
    0.06
    åĪ©æĸ¯
    0.06
    æ´»äºĨ
    0.06
    ujud
    0.06
     Pela
    0.06
    ä½łæĺ¯æĪij
    0.06
    etar
    0.06
    _compat
    0.06
    Activations Density 0.102%

    No Known Activations