© 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. 3278
    Prev
    Next
    INDEX
    Explanations

    verb endings

    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
    å¾Ĺä¸Ĭ
    -0.09
    ings
    -0.07
    até
    -0.07
    gate
    -0.07
    ure
    -0.07
    upp
    -0.07
    ingga
    -0.07
    ãģĭãĤĬ
    -0.07
     ancor
    -0.06
     easily
    -0.06
    POSITIVE LOGITS
     lately
    0.08
     ì¤ijìĿ´ëĭ¤
    0.08
    ukan
    0.08
    åīįæīĢæľªæľīçļĦ
    0.08
    oldt
    0.08
    urve
    0.08
    åıĪä¸įæĺ¯
    0.08
    /loading
    0.08
    ä¸Ńãģ§
    0.08
    uert
    0.08
    Activations Density 0.943%

    No Known Activations