© 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. 26431
    Prev
    Next
    INDEX
    Explanations

    examples using such as or like

    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
    æĿIJæĸĻåıĬ
    -0.07
     dess
    -0.07
    AndGet
    -0.07
    åIJĦæł¡
    -0.07
    åĿŁå¢ĵ
    -0.07
    éĢĬ
    -0.07
     âĢ¦.
    -0.07
    åĨħ容åıĬ
    -0.07
     Tender
    -0.07
    ä½ľåĵģåĨħ容
    -0.07
    POSITIVE LOGITS
     ours
    0.10
     yours
    0.09
     halnya
    0.08
    åĴ±ä»¬çļĦ
    0.08
    bose
    0.07
    ä½łæĪij
    0.07
    EXIST
    0.07
    åĴ±
    0.07
    åħ¸åŀĭçļĦ
    0.07
     ones
    0.07
    Activations Density 0.138%

    No Known Activations