© 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. 38842
    Prev
    Next
    INDEX
    Explanations

    specific dates and durations

    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
    éĽªæ¢¨
    -0.08
    शा
    -0.07
    宿
    -0.07
    è´¤
    -0.07
    æŀ
    -0.07
    æĨ©
    -0.07
    è³¢
    -0.07
    æį²
    -0.07
    Ïģή
    -0.07
    ÅĽ
    -0.06
    POSITIVE LOGITS
    ubu
    0.07
    çī¹æ®ĬçļĦ
    0.07
    å¼łæµ·
    0.07
    ÑħаÑĢ
    0.07
    ups
    0.07
    大éĩıçļĦ
    0.07
    çļĦçī¹èī²
    0.06
    Collapsed
    0.06
    pak
    0.06
     Yup
    0.06
    Activations Density 0.441%

    No Known Activations