© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 58335
    Prev
    Next
    INDEX
    Explanations

    Cameron, Putin, `+`

    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
    ards
    -0.08
     &$
    -0.07
    ört
    -0.07
    tev
    -0.07
    ono
    -0.07
     Grove
    -0.07
    нÑİ
    -0.07
    aille
    -0.07
    pon
    -0.06
    æĥħåĨµæĿ¥çľĭ
    -0.06
    POSITIVE LOGITS
    丽èİİ
    0.09
    æĻĮ
    0.07
    sang
    0.07
    ingen
    0.07
    尼迪
    0.07
    adhan
    0.07
    æģ¯
    0.07
    å¿ĥåŃĺ
    0.07
    å¿ĥç¥ŀ
    0.06
    (D
    0.06
    Activations Density 0.001%

    No Known Activations