© 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. 49391
    Prev
    Next
    INDEX
    Explanations

    Russian scientific terms

    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
    kering
    -0.08
    计ç®Ĺåħ¬å¼ı
    -0.08
    າ
    -0.08
    QRST
    -0.08
    waan
    -0.08
     kalkul
    -0.08
     Presup
    -0.08
    creenshot
    -0.08
    alculate
    -0.08
    нваÑĢ
    -0.08
    POSITIVE LOGITS
     observation
    0.06
    .flag
    0.06
    /english
    0.06
    m
    0.06
    observations
    0.06
     observations
    0.06
     Wis
    0.05
    ÏĩÏħ
    0.05
    hea
    0.05
    æ¦Ĥ念
    0.05
    Activations Density 0.306%

    No Known Activations