© 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. 990
    Prev
    Next
    INDEX
    Explanations

    math expressions and "units"

    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
    äg
    -0.08
    以ä¸ĭæĺ¯å°ıç¼ĸ
    -0.08
    ANH
    -0.08
    ennen
    -0.07
    IVEN
    -0.07
    andex
    -0.07
    麾
    -0.07
    æľ¬åľºæ¯ĶèµĽ
    -0.07
    ä¸ĭéĿ¢æĺ¯å°ıç¼ĸ
    -0.07
    AIN
    -0.07
    POSITIVE LOGITS
     vét
    0.06
    оби
    0.05
    usra
    0.05
    topl
    0.05
    atha
    0.05
    heed
    0.05
    润åıij
    0.05
    rano
    0.05
    çļĦéĩį
    0.05
    ÂŃs
    0.05
    Activations Density 0.004%

    No Known Activations