© 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. 33531
    Prev
    Next
    INDEX
    Explanations

    formula

    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
     ÙĪسÙĦ
    -0.07
    ÄIJT
    -0.07
    åı¯æĥ³
    -0.07
    ế
    -0.07
    opa
    -0.07
    åij½çļĦ
    -0.07
    åIJĦç§į
    -0.06
    elus
    -0.06
     Demonstr
    -0.06
    åķĨåĵģä¿¡æģ¯
    -0.06
    POSITIVE LOGITS
    åħ¬å¼ı
    0.10
     formula
    0.09
    计ç®Ĺåħ¬å¼ı
    0.08
    ê¶Į
    0.08
    formula
    0.08
     Formula
    0.07
    eneric
    0.07
     fórmula
    0.07
    ecta
    0.07
     formulas
    0.07
    Activations Density 0.005%

    No Known Activations