© 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. 21979
    Prev
    Next
    INDEX
    Explanations

    logical quantifiers and symbols

    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
    ometri
    -0.07
    legates
    -0.07
    æīİæīİå®ŀ
    -0.07
    ÙĬÙĥ
    -0.07
    emente
    -0.07
    dent
    -0.06
     каÑĩ
    -0.06
    stek
    -0.06
    oar
    -0.06
     jubil
    -0.06
    POSITIVE LOGITS
    utex
    0.07
    ä¸Ģ个åı«
    0.07
    æľīæĦŁ
    0.06
     пого
    0.06
    åį«
    0.06
     hạn
    0.06
    éĶĻé¢ĺ
    0.06
     theor
    0.06
    Ùĩاب
    0.06
    æ¼Ķç»İ
    0.06
    Activations Density 0.003%

    No Known Activations