© 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. 61249
    Prev
    Next
    INDEX
    Explanations

    basic units or building blocks

    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
    à¹ĥà¸Ļรà¸Ńà¸ļ
    -0.08
    æľīä¸Ģ次
    -0.07
    ä¸Ģå¹´å¤ļ
    -0.07
     diversion
    -0.07
    lfw
    -0.06
    بÙĩØ©
    -0.06
    å°±å¾Ī容æĺĵ
    -0.06
    Æ¯ÆłNG
    -0.06
    åĩłæ¬¡
    -0.06
    ä¸Ģ个æľĪ
    -0.06
    POSITIVE LOGITS
    å¾®è§Ĥ
    0.09
    åİŁåŃIJ
    0.08
     microscopic
    0.08
    æĽ´å°ı
    0.08
    æĺ¾å¾®
    0.08
     atom
    0.08
    æľĢå°ıçļĦ
    0.08
     smallest
    0.07
    è¿ĻäºĽä¸ľè¥¿
    0.07
    ucle
    0.07
    Activations Density 0.005%

    No Known Activations