© 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. 20756
    Prev
    Next
    INDEX
    Explanations

    commands and data operations

    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
    æĺ¯ä»Ģä¹Īåij¢
    -0.07
    èijĹçļĦ
    -0.07
    filesize
    -0.07
    è¿Ļ个è§Ĵèī²
    -0.07
    åIJĪçIJĨåĪ©çĶ¨
    -0.07
    astos
    -0.07
    æĦıåľ¨
    -0.07
    rau
    -0.06
    åı¦å¤ĸä¸Ģ个
    -0.06
    æ°Ľ
    -0.06
    POSITIVE LOGITS
    åĴĮçIJĨ解
    0.07
    æĹłè®ºä½łæĺ¯
    0.06
    klam
    0.06
    raison
    0.06
    å¾ħ
    0.06
    åįĹ
    0.06
    erce
    0.06
    лим
    0.06
    veen
    0.06
    ÑģÑĥÑĢ
    0.06
    Activations Density 0.002%

    No Known Activations