© 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. 18710
    Prev
    Next
    INDEX
    Explanations

    programming operations or concepts

    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
    ney
    -0.07
    ky
    -0.07
    cky
    -0.06
    KY
    -0.06
    æĺ¯ä¸Ģ家以
    -0.06
    erman
    -0.06
    DataAdapter
    -0.06
    为人
    -0.06
    enant
    -0.06
    rieben
    -0.06
    POSITIVE LOGITS
    ä¸įä»ħåľ¨
    0.09
    èo
    0.08
     nejen
    0.08
    æħµ
    0.08
    äºĨæķ´ä¸ª
    0.07
    InChildren
    0.07
    çī©çIJĨ
    0.07
     odst
    0.07
    çļĦçī©çIJĨ
    0.07
    amas
    0.07
    Activations Density 0.105%

    No Known Activations