© 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. 26461
    Prev
    Next
    INDEX
    Explanations

    equations with $ and =

    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
    enty
    -0.08
    entif
    -0.08
    éĥ
    -0.07
    å©¿
    -0.07
    ç»°
    -0.07
    estina
    -0.07
    _tools
    -0.07
    νά
    -0.07
    ogos
    -0.07
    UnitTest
    -0.07
    POSITIVE LOGITS
    èĢĮä¸Ķè¿ĺ
    0.06
    ä¸Ķ
    0.06
    éĤ£éº¼
    0.06
    åIJİå¸Ĥ
    0.06
     implies
    0.06
    rav
    0.06
    åIJĮå¿Ĺ
    0.06
     imply
    0.06
    就说æĺİ
    0.06
    ä¸Ģè§Ĵ
    0.06
    Activations Density 0.027%

    No Known Activations