© 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. 25175
    Prev
    Next
    INDEX
    Explanations

    names and proposals

    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
    åĬłåħ¥æĶ¶èĹı
    -0.09
    æľĢè¿ijæĽ´æĸ°
    -0.08
    çĥŃéŨæłĩçŃ¾
    -0.08
    zzo
    -0.08
    çļĦçİ°çĬ¶
    -0.08
    æĪijçļĦè¯Ŀ
    -0.08
    ä»»ä½ķçļĦ
    -0.08
    _clr
    -0.08
    æĽ´æĸ°æĹ¥æľŁ
    -0.08
    æħ§èģª
    -0.08
    POSITIVE LOGITS
     seminal
    0.12
    æľĢæĹ©
    0.11
    åİŁå§ĭ
    0.10
     pioneering
    0.10
     originally
    0.10
    æľĢåĪĿçļĦ
    0.10
    å½ĵå¹´
    0.09
     famously
    0.09
    å¼ĢåĪĽ
    0.09
    åİŁå§ĭçļĦ
    0.09
    Activations Density 0.202%

    No Known Activations