© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23076
    Prev
    Next
    INDEX
    Explanations

    which introduces consequence

    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
    auc
    -0.07
    缮ä¸į
    -0.07
    åĬĽä½ľ
    -0.07
    æľīä»»ä½ķ
    -0.07
    èĩªç¼ĸ
    -0.07
     Ø¢ÙĨÚĨÙĩ
    -0.07
    åIJĿ
    -0.07
    ม
    -0.07
    DED
    -0.07
     ugyanis
    -0.07
    POSITIVE LOGITS
     بدÙĪرÙĩ
    0.10
    ä¹Łå°±æĦıåij³çĿĢ
    0.09
     ultimately
    0.08
     means
    0.08
    izzo
    0.08
     resulted
    0.08
    etto
    0.07
    çļĦç»ĵæŀľ
    0.07
    means
    0.07
    ä¹Łå°±æĺ¯
    0.07
    Activations Density 0.309%

    No Known Activations