© 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. 49519
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols in 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
     Ranked
    -0.07
    chow
    -0.07
    erne
    -0.07
    alus
    -0.07
    itere
    -0.07
    нена
    -0.07
    illen
    -0.07
    illy
    -0.07
    Ranked
    -0.06
    æľĢåĸľæ¬¢
    -0.06
    POSITIVE LOGITS
    è¾Ħ
    0.07
    ç¾İå¾·
    0.07
     ÑıкобÑĭ
    0.07
    Misc
    0.07
    å¾·éŁ³
    0.07
    缸åħ³æݨèįIJ
    0.07
     arro
    0.07
    รว
    0.07
    å°±åıĺæĪIJäºĨ
    0.06
    ÑĢиÑĦ
    0.06
    Activations Density 0.006%

    No Known Activations