© 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. 8274
    Prev
    Next
    INDEX
    Explanations

    end or last part of something

    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
     elsewhere
    -0.08
     Wolff
    -0.08
     somewhere
    -0.07
    æ¯Ķåݻ年åIJĮæľŁ
    -0.07
    ä½ķåľ°
    -0.07
    ä¸ŃæŬ
    -0.07
    ÙĪسÛĮ
    -0.07
    åIJĮæľŁ
    -0.07
    _pitch
    -0.07
    .raise
    -0.07
    POSITIVE LOGITS
    åĴĮæľĢ
    0.12
    æľ«
    0.10
    -end
    0.10
    สุà¸Ķ
    0.10
     edge
    0.09
     extremo
    0.09
     extreme
    0.09
     end
    0.09
    端
    0.09
    ,last
    0.09
    Activations Density 0.177%

    No Known Activations