© 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. 56084
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with numbers

    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
     Barrel
    -0.08
    ulses
    -0.08
    ordes
    -0.07
    ä¾ĽåĽ¾
    -0.07
    >(*
    -0.07
    çīĪæĿĥä¸İåħį责声æĺİ
    -0.07
    UNC
    -0.07
    âĢ¦âĢ¦ãĢĤ
    -0.07
    ][-
    -0.07
    èĬ¥
    -0.07
    POSITIVE LOGITS
    æª
    0.08
    ä¹ı
    0.07
    åĮĪ
    0.07
    æģ¤
    0.07
    ×ķ×IJ
    0.06
    让广大
    0.06
    翱
    0.06
    éĿĴè¡£
    0.06
    æľīåĵªäºĽ
    0.06
    atch
    0.06
    Activations Density 0.036%

    No Known Activations