© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22717
    Prev
    Next
    INDEX
    Explanations

    listing items or describing essentials

    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
    ilde
    -0.08
    érc
    -0.07
    pital
    -0.07
    Invoke
    -0.07
    odore
    -0.07
     Triumph
    -0.06
    èĤ¯å¾·åŁº
    -0.06
    ×ķ׼
    -0.06
    زة
    -0.06
    åīįåºĶ
    -0.06
    POSITIVE LOGITS
    ä¸įè¾ŀ
    0.07
    åľ¨è§Ħå®ļæŶéĹ´åĨħ
    0.07
    atur
    0.07
    伺åĢĻ
    0.07
    ÙĪرÛĮ
    0.06
     вÑĭÑħод
    0.06
    aku
    0.06
    аÑĤÑĥÑĢа
    0.06
    aksim
    0.06
    为åħ¨çIJĥ
    0.06
    Activations Density 0.001%

    No Known Activations