© 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. 27900
    Prev
    Next
    INDEX
    Explanations

    transaction limit

    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
    abort
    -0.08
     huge
    -0.08
    éĺħè¯»æľ¬æĸĩåīį
    -0.07
     goodies
    -0.07
    åĬłåħ¥ä¹¦çŃ¾
    -0.07
    ÙĪÙĨا
    -0.07
     HUGE
    -0.07
    æ´»åĬ¨ä¸Ńå¿ĥ
    -0.07
    è¿Ļ个大
    -0.07
    çĶŁæ´»ãĤĴ
    -0.07
    POSITIVE LOGITS
    é¦ģ
    0.07
    äºĨ解ä¸Ģä¸ĭåIJ§
    0.06
    isir
    0.06
    ç¡
    0.06
    缸åºĶçļĦ
    0.06
     tersebut
    0.06
    º
    0.06
    缸åħ³ä¸ĵä¸ļ
    0.06
    ancements
    0.05
    çIJĨæīĢ
    0.05
    Activations Density 0.004%

    No Known Activations