© 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. 9231
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with parentheses and square roots

    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
    imer
    -0.08
    izzle
    -0.08
    äºijé£ŀ
    -0.08
    parg
    -0.07
    akor
    -0.07
    .constructor
    -0.07
    uis
    -0.07
    IMER
    -0.07
    ão
    -0.07
    åıĸæł·
    -0.07
    POSITIVE LOGITS
     unused
    0.06
    ÑĥлÑĮÑĤ
    0.06
    人æĿ¥
    0.06
    ÑĢов
    0.06
    sic
    0.06
    使ãģĪãĤĭ
    0.06
    iros
    0.06
     viss
    0.06
    iro
    0.06
     allowed
    0.06
    Activations Density 0.008%

    No Known Activations