© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21593
    Prev
    Next
    INDEX
    Explanations

    small and large quantities

    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
    קר
    -0.08
    ä¸İä¼Ĺ
    -0.08
    å¢ĥåĨħçļĦ
    -0.08
    amah
    -0.07
    ãĥ¼ãĥģ
    -0.07
    à¹Ģà¸ĭà¸Ńรà¹Į
    -0.07
    ihak
    -0.07
    å·¥ä½ľæ»¡
    -0.07
    æģ¤
    -0.07
    orris
    -0.07
    POSITIVE LOGITS
    ness
    0.12
    -ish
    0.10
    -looking
    0.09
     جداÙĭ
    0.09
    NESS
    0.09
    à¹Ĩ
    0.09
     enough
    0.09
     جدÙĭا
    0.09
    est
    0.08
     ×ŀ×IJ×ķ×ĵ
    0.08
    Activations Density 0.005%

    No Known Activations