© 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. 40500
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation

    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
    ,
    -0.09
    "
    -0.07
    is
    -0.06
    çľĭ
    -0.06
    (
    -0.06
    in
    -0.06
    —
    -0.06
    è¿Ļ个
    -0.06
    .
    -0.06
    ↵
    -0.05
    POSITIVE LOGITS
    ptime
    0.10
    aaS
    0.09
    æľīæīĢæĢĿ
    0.09
     –**
    0.09
    Animate
    0.09
    δÏĮ
    0.09
    ainya
    0.09
    wär
    0.09
    ÅĤów
    0.08
    å·´åħĭ
    0.08
    Activations Density 0.024%

    No Known Activations