© 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. 60976
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

    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
    èĥ¶è´¨
    -0.07
    å°±å¤ļ
    -0.07
    rael
    -0.06
    çľģå¿ĥ
    -0.06
    /run
    -0.06
     just
    -0.06
    æ¯ıä¸ĢåIJį
    -0.06
    istri
    -0.06
    TabPage
    -0.06
    åĩłåıª
    -0.06
    POSITIVE LOGITS
    pje
    0.07
    tat
    0.07
    tora
    0.07
    延伸éĺħ读
    0.07
    å¹ħ
    0.06
    å¿ĥæĻº
    0.06
    磩
    0.06
    ÑıÑģ
    0.06
    ä½łä¸Ģå®ļè¦ģ
    0.06
     unthinkable
    0.06
    Activations Density 0.027%

    No Known Activations