© 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. 61942
    Prev
    Next
    INDEX
    Explanations

    linking: https, 1, But

    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
    tock
    -0.09
    èĩªå·±çļĦ人
    -0.09
    cket
    -0.08
    -slot
    -0.08
    åĴĮ社ä¼ļä¿Ŀéļľ
    -0.08
    _MET
    -0.08
    æ¡ĵ
    -0.08
    èĢĮçŁ¥
    -0.08
    ستÛĮ
    -0.08
    ä½įåľ¨
    -0.08
    POSITIVE LOGITS
    ä»ĩ
    0.06
    èŀį
    0.06
    äºŃ
    0.06
    _literals
    0.06
    nea
    0.06
    èĤ¯å®ļçļĦ
    0.06
    人éĹ´
    0.06
    å¿
    0.05
    确认
    0.05
    åIJĪåĬĽ
    0.05
    Activations Density 0.001%

    No Known Activations