© 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. 31464
    Prev
    Next
    INDEX
    Explanations

    large quantity or size

    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
    æĸ°å½¢åĬ¿
    -0.08
    best
    -0.08
    æ°¸èijĨ
    -0.08
    åĪĿå¿ĥ使åij½
    -0.07
    æľĢä½³
    -0.07
    aur
    -0.07
    noÅĽciÄħ
    -0.07
    é«ĺè°ĥ
    -0.07
    esc
    -0.07
    æĢ¥æĢ¥
    -0.07
    POSITIVE LOGITS
     amount
    0.12
     amounts
    0.12
    ä¸įå°ıçļĦ
    0.10
    -sized
    0.10
    /sign
    0.09
    amount
    0.09
    ç¨ĭ度çļĦ
    0.09
    äºĨä¸Ģçķª
    0.09
    éĩıçļĦ
    0.09
     sized
    0.09
    Activations Density 0.339%

    No Known Activations