© 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. 44384
    Prev
    Next
    INDEX
    Explanations

    concept, components, common, important, key, class, complication

    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
    æľĽè¿ľ
    -0.09
    -lang
    -0.08
    æ»¡çĽ®
    -0.08
     provin
    -0.07
     INCLUDING
    -0.07
    omp
    -0.07
    ¶
    -0.07
    .(*
    -0.07
    ÒĽÑĤÑĭ
    -0.07
    åľ¨è¿Ļç§įæĥħåĨµä¸ĭ
    -0.07
    POSITIVE LOGITS
    éĩįè¦ģçļĦ
    0.09
    çļĦéĩįè¦ģç»ĦæĪIJéĥ¨åĪĨ
    0.09
    ä¸Ģ个éĩįè¦ģ
    0.09
    ä¸ŃçļĦéĩįè¦ģ
    0.09
    çļĦéĩįè¦ģ
    0.09
    çļĦéĩįè¦ģåĨħ容
    0.08
     important
    0.08
     ì¤ijìļĶíķľ
    0.08
    éĩįè¦ģ
    0.08
    çŃīéĩįè¦ģ
    0.07
    Activations Density 0.396%

    No Known Activations