© 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. 45596
    Prev
    Next
    INDEX
    Explanations

    caps and debut

    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
    åĩºçĤī
    -0.07
    ÑĢк
    -0.07
    åľ¨ä¸Ģå®ļ
    -0.07
    ç¦»åľº
    -0.07
    abu
    -0.07
    çIJĨæĢ§
    -0.07
    ä¾Ŀæ³ķæ²»
    -0.06
    azgo
    -0.06
    ration
    -0.06
    ottom
    -0.06
    POSITIVE LOGITS
     appearances
    0.11
    æĸŃç»Ń
    0.10
    ä½ľä¸ºä¸ĢåIJį
    0.10
    åıĤä¸İäºĨ
    0.09
     solo
    0.09
     ÑĥÑĩаÑģÑĤиÑı
    0.09
     assignments
    0.08
    åıĤåĬłäºĨ
    0.08
    Appear
    0.08
     versatility
    0.08
    Activations Density 1.039%

    No Known Activations