© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 37454
    Prev
    Next
    INDEX
    Explanations

    once you know

    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
    Negative Logits
    æļĤ
    -0.07
    æļĤæŶ
    -0.07
    æŃ£åĢ¼
    -0.07
    ujur
    -0.07
    èĬ³èįī
    -0.06
    æŃ£å¥½
    -0.06
    翼翼
    -0.06
    åİī
    -0.06
     temporarily
    -0.06
    å¯Ħè¯Ń
    -0.06
    POSITIVE LOGITS
    ãģĤãģ¨ãģ¯
    0.12
    å¾Įãģ¯
    0.09
    å°±å¾Ī容æĺĵ
    0.09
    就容æĺĵ
    0.09
    è±ģçĦ¶
    0.08
     ÑıÑģ
    0.08
    ä¸ĢæŦ
    0.08
     ease
    0.08
    raga
    0.08
    easy
    0.07
    Activations Density 0.091%

    No Known Activations