© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10929
    Prev
    Next
    INDEX
    Explanations

    pronouns and actions

    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
    ิà¹Īม
    -0.09
    ç»ĻæĪijçķĻè¨Ģ
    -0.08
    λεÏį
    -0.07
    accro
    -0.07
    ç½ijç«Ļ导èĪª
    -0.07
     Giardino
    -0.07
    letes
    -0.07
    æ¯Ķåݻ年
    -0.07
    essel
    -0.07
    ä¸įæĦ§æĺ¯
    -0.07
    POSITIVE LOGITS
    è§Ĥå¯Ł
    0.08
    为åħ¶
    0.08
    `s
    0.07
    çľĭåľ¨çľ¼éĩĮ
    0.07
    ä¸İä¹ĭ
    0.07
    çĮľæµĭ
    0.07
    åľ¨åħ¶ä¸Ń
    0.07
    è¦ģæ±Ĥåħ¶
    0.07
    ä»İä¸Ń
    0.07
    åıĤä¸İåħ¶ä¸Ń
    0.07
    Activations Density 0.311%

    No Known Activations