© 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. 21369
    Prev
    Next
    INDEX
    Explanations

    errors and technical issues

    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
    ä¸ĢåĽŀ
    -0.08
    èĦĤèĤªèĤĿ
    -0.08
    heb
    -0.07
    åīį款
    -0.07
    çļĦåįļ客
    -0.07
    aktu
    -0.07
    ông
    -0.07
    irman
    -0.07
    西游
    -0.07
    é»ĦåŁĶ
    -0.07
    POSITIVE LOGITS
    åį¡çļĦ
    0.07
     phú
    0.07
     Gram
    0.06
    æĬĺæī£
    0.06
    ania
    0.06
     Tav
    0.06
     Rum
    0.06
    alt
    0.06
     T
    0.06
    ÑĢд
    0.06
    Activations Density 1.473%

    No Known Activations