© 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. 59764
    Prev
    Next
    INDEX
    Explanations

    `optimization and comparison of methods`

    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
    _SIGN
    -0.07
    ools
    -0.07
    æ´ŀ
    -0.06
     lib
    -0.06
    çī§
    -0.06
     dimensions
    -0.06
     trump
    -0.06
    ÃŃv
    -0.06
    æĥĬ
    -0.05
    令
    -0.05
    POSITIVE LOGITS
    åħ¶ä»ĸæĸ¹å¼ı
    0.15
    è¿Ļç§įæĸ¹æ³ķ
    0.12
    è¿Ļ个æĸ¹æ³ķ
    0.12
    ä¸Ģç§įæĺ¯
    0.11
     berbasis
    0.10
    该æĸ¹æ³ķ
    0.10
    åĪĨæŀIJæ³ķ
    0.10
    æĸ¹æ³ķè¿Ľè¡Į
    0.10
    çŃīæĸ¹æ³ķ
    0.10
    ä¼łç»ŁçļĦ
    0.10
    Activations Density 0.426%

    No Known Activations