© 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. 60840
    Prev
    Next
    INDEX
    Explanations

    ever, unimaginable, utmost

    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
    пÑĢ
    -0.08
    åħ®
    -0.07
    并ä¸įèĥ½
    -0.07
    çī¹å¾ģæĺ¯
    -0.07
    óln
    -0.07
    åľ¨æŁIJäºĽ
    -0.07
    phin
    -0.07
    _OVER
    -0.06
    à¦ķà§įষ
    -0.06
    ä¸ĢäºĽå°ı
    -0.06
    POSITIVE LOGITS
     ever
    0.11
     ÙĪØ£Ùĥثر
    0.11
     اÙĦإطÙĦاÙĤ
    0.09
     überhaupt
    0.09
     ooit
    0.09
     vůbec
    0.09
     jamás
    0.08
    Ever
    0.08
     imaginable
    0.08
     EVER
    0.07
    Activations Density 0.428%

    No Known Activations