© 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. 47578
    Prev
    Next
    INDEX
    Explanations

    repeat

    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
    究竣æĺ¯ä»Ģä¹Ī
    -0.07
    è¾±
    -0.07
    οÏħÏģγ
    -0.07
    çı¾
    -0.07
    æĤ¬æµ®
    -0.07
    ÏĢοι
    -0.07
    áĢĽáĢ¬
    -0.07
    çıį
    -0.07
    æĹ¥å¸¸
    -0.07
     suspended
    -0.06
    POSITIVE LOGITS
     repeat
    0.11
    repeat
    0.10
    éĩįå¤į
    0.10
     repeats
    0.10
    为äºĨéģ¿åħį
    0.09
    æ¸Īãģ¿
    0.09
    Repeat
    0.09
     ì¤ijë³µ
    0.09
     repetir
    0.09
     повÑĤоÑĢ
    0.09
    Activations Density 0.069%

    No Known Activations