© 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. 20789
    Prev
    Next
    INDEX
    Explanations

    often called, referred to, designated

    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
     tadi
    -0.07
    -0.06
    è¯Ŀ
    -0.06
    å®´
    -0.06
    åĽ¢çļĦ
    -0.06
    alance
    -0.06
    éĻ©äºĽ
    -0.06
    åİŁæľ¬çļĦ
    -0.06
    æŁIJç§įç¨ĭ度ä¸Ĭ
    -0.06
    åĩºå®¶
    -0.06
    POSITIVE LOGITS
    avar
    0.08
     denote
    0.08
    upu
    0.08
    riad
    0.08
     denotes
    0.07
    koz
    0.07
    cron
    0.07
    表è¨ĺ
    0.07
     abbrev
    0.07
    éĻ¤éĿŀ
    0.07
    Activations Density 0.088%

    No Known Activations