© 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. 12216
    Prev
    Next
    INDEX
    Explanations

    code examples and explanations

    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
    bourne
    -0.08
    ä¸ĭåľº
    -0.07
    éĵ¡
    -0.07
    é¦Ħ饨
    -0.07
    绪
    -0.07
    licit
    -0.07
     óp
    -0.07
    &E
    -0.07
    urator
    -0.07
    holm
    -0.07
    POSITIVE LOGITS
    ä¼¼ä¹İåľ¨
    0.09
    æĹ¨åľ¨
    0.09
    æĺ¯çĶ¨æĿ¥
    0.09
    ä¼¼ä¹İ
    0.09
     apparently
    0.08
    ä¼¼ä¹İæĺ¯
    0.08
    çĶ¨æĿ¥
    0.08
     basically
    0.08
    è¯ķåĽ¾
    0.08
     essentially
    0.08
    Activations Density 0.069%

    No Known Activations