© 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. 26928
    Prev
    Next
    INDEX
    Explanations

    size, quantity, intensity

    np_acts-logits-general · gemini-2.5-flash-lite

    adjectives describing large quantities, sizes, or magnitudes.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jrosseruk
    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
     تÙĤرÙĬب
    -0.10
    cheon
    -0.07
    éĥ¨åĪĨåĨħ容
    -0.07
    иÑĤоÑĢ
    -0.07
    жом
    -0.07
     reasonably
    -0.07
     Sieg
    -0.07
    inqui
    -0.07
    åºĶ该ä¸įä¼ļ
    -0.06
    åĨįæİ¥åĨįåİī
    -0.06
    POSITIVE LOGITS
     جداÙĭ
    0.14
     جدÙĭا
    0.14
     sekali
    0.12
     ×ŀ×IJ×ķ×ĵ
    0.11
     banget
    0.11
     ÙĦÙĦغاÙĬØ©
    0.11
    æĹłæ¯ĶçļĦ
    0.11
    issimo
    0.10
    ÃŃsimo
    0.10
    èĩ³æŀģ
    0.10
    Activations Density 0.312%

    No Known Activations