© 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. 41515
    Prev
    Next
    INDEX
    Explanations

    picking letters from sets, documents, questions

    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
    enca
    -0.07
    æĢ»ç®¡
    -0.07
    FP
    -0.07
    主åĭķ
    -0.07
    DDL
    -0.07
     Ade
    -0.07
    коно
    -0.07
    åľ°åIJij
    -0.07
    aked
    -0.07
    PageRoute
    -0.07
    POSITIVE LOGITS
    è§Ĥ念åĴĮ
    0.07
    ä¸įæŃ£ç¡®çļĦæĺ¯
    0.07
    åIJ¸
    0.06
    éĶĻ误çļĦæĺ¯
    0.06
    çĶ¨åĪ°çļĦ
    0.06
    عÙĦÙĤ
    0.06
    æī«ä¸Ģæī«
    0.06
    ifact
    0.06
     deal
    0.06
    shit
    0.06
    Activations Density 0.001%

    No Known Activations