© 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. 60936
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and fractions

    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
    oline
    -0.08
    emar
    -0.08
    odem
    -0.07
    brug
    -0.07
    è·Įåģľ
    -0.07
    aign
    -0.07
    çĤľ
    -0.07
    udit
    -0.06
    ¯
    -0.06
    idé
    -0.06
    POSITIVE LOGITS
    ìĿ´íĬ¸
    0.07
    æĭįçļĦ
    0.07
    åŃIJç³»ç»Ł
    0.07
    ĥģ
    0.07
     fractions
    0.07
    ãĤµãĥĸ
    0.06
    жда
    0.06
    ľ
    0.06
    £
    0.06
    chau
    0.06
    Activations Density 0.002%

    No Known Activations