© 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. 31954
    Prev
    Next
    INDEX
    Explanations

    when `var` or `may`

    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
    çª
    -0.07
    effective
    -0.06
    æĹ
    -0.06
    å¦Ĥåľ¨
    -0.06
    æIJ
    -0.06
    либо
    -0.06
    åĪĩåĭ¿
    -0.06
    ektor
    -0.06
    ulator
    -0.06
    aman
    -0.06
    POSITIVE LOGITS
    ipsis
    0.08
    cera
    0.08
    çĺ¦èº«
    0.07
    zit
    0.07
    meli
    0.07
    å·²ç»ıæĬĬ
    0.07
    å±±éķĩ
    0.07
    çĶ¨çļĦæĺ¯
    0.07
    ẩn
    0.07
    çİĭæĺŁ
    0.07
    Activations Density 0.034%

    No Known Activations