© 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. 39796
    Prev
    Next
    INDEX
    Explanations

    non-

    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
    IMIT
    -0.08
    驻马
    -0.08
    ALA
    -0.08
    ä¸įåĥı
    -0.08
    çīĽç¾Ĭ
    -0.07
    mack
    -0.07
    ======
    -0.07
    agem
    -0.07
    ä¸įèĥ½è¶ħè¿ĩ
    -0.07
    igate
    -0.07
    POSITIVE LOGITS
    (non
    0.12
    /non
    0.11
    æĪĸéĿŀ
    0.08
    es
    0.08
    åĴĮéĿŀ
    0.07
    ä½ĨåıĪ
    0.07
    uses
    0.07
     بÙĥØ«ÙĬر
    0.07
    èĢĮæĺ¯
    0.06
     than
    0.06
    Activations Density 0.104%

    No Known Activations