© 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. 30502
    Prev
    Next
    INDEX
    Explanations

    Fibonacci, biblical, FIFA

    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
    以ä¸Ĭå°±æĺ¯å°ıç¼ĸ
    -0.09
    OfFile
    -0.07
    azzo
    -0.07
    ä¸ĭåĬŁå¤«
    -0.07
    以ä¸Ĭå°±æĺ¯åħ³äºİ
    -0.07
    manship
    -0.07
    FUL
    -0.07
    elijke
    -0.07
    salt
    -0.07
    Ø©
    -0.07
    POSITIVE LOGITS
    áĥĴáĥł
    0.09
    æķ°åĪĹ
    0.08
    plorer
    0.08
    ç³»
    0.07
     numbers
    0.07
    inear
    0.07
    NECT
    0.06
    並ãģ³
    0.06
    éĢŁéĢĴ
    0.06
    onacci
    0.06
    Activations Density 0.001%

    No Known Activations