© 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. 28734
    Prev
    Next
    INDEX
    Explanations

    punctuation and articles

    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
    声ä¸Ń
    -0.08
    ettava
    -0.07
    ÏĩοÏĤ
    -0.07
    nowrap
    -0.07
    inking
    -0.07
    acker
    -0.07
    -caret
    -0.07
    åIJĪ
    -0.07
    ikus
    -0.07
    å°ıåĪ°
    -0.07
    POSITIVE LOGITS
    uw
    0.07
    ordan
    0.07
    æĥħåĨµçļĦ
    0.06
    ily
    0.06
    å°ĨæĮīçħ§
    0.06
    erden
    0.06
    æĺ¯ä¸įä¼ļ
    0.06
    éĻIJãĤĬ
    0.06
    æľī两个
    0.06
    pond
    0.06
    Activations Density 0.001%

    No Known Activations