© 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. 13579
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
    Õ¡Õ£
    -0.08
    éĩįå·¥
    -0.07
    esty
    -0.07
    áĥĵáĥĺ
    -0.07
    ÐijÑĭ
    -0.07
    ÛĮاÙĨ
    -0.07
    oppi
    -0.07
     Taller
    -0.07
    inom
    -0.07
    æ©ŁåĻ¨
    -0.07
    POSITIVE LOGITS
    åħ°å¾·
    0.08
    lobe
    0.07
    gel
    0.07
    lo
    0.07
    é¢ĸ
    0.07
    âĢ¦âĢ¦ãĢĤ
    0.07
    æį
    0.07
     jej
    0.07
    ç¼ĸ
    0.07
    å±Ĥ次æĦŁ
    0.07
    Activations Density 0.090%

    No Known Activations