© 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. 26826
    Prev
    Next
    INDEX
    Explanations

    China township

    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
    nya
    -0.09
    wechsel
    -0.08
    ison
    -0.08
    araf
    -0.07
    ç¥ŀçİĭ
    -0.07
    sene
    -0.07
    ourcen
    -0.07
     conto
    -0.07
    èij±èij±
    -0.07
    ä¸įç´Ĭ
    -0.07
    POSITIVE LOGITS
    å·¥ç¨ĭéĻ¢
    0.11
    å·¥ç¨ĭéĻ¢éĻ¢å£«
    0.10
    eshire
    0.09
    åĴĮä¸ĸçķĮ
    0.09
    çī¹èī²çļĦ
    0.09
    erokee
    0.09
    å¢ĥåĨħçļĦ
    0.08
    ephy
    0.08
    çīĪçļĦ
    0.08
    åĴĮæĹ¥æľ¬
    0.08
    Activations Density 0.028%

    No Known Activations