© 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. 4085
    Prev
    Next
    INDEX
    Explanations

    average, mean, estimator

    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
     اÙĦشر
    -0.07
    -encoded
    -0.07
     encoding
    -0.07
    ç¼ĸçłģ
    -0.07
    åŁĭèij¬
    -0.07
    &e
    -0.07
     غد
    -0.07
    encoding
    -0.07
    çĮ«çļĦ
    -0.07
    cko
    -0.07
    POSITIVE LOGITS
    ipples
    0.07
    ì§ij
    0.07
    æł·æľ¬
    0.07
    æ¼Ĥæµ®
    0.07
    空å¿ĥ
    0.07
    çŃı
    0.07
     Spiegel
    0.07
    å°ıç»Ħ
    0.07
    áu
    0.07
    åģıå·®
    0.07
    Activations Density 0.003%

    No Known Activations