© 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. 63622
    Prev
    Next
    INDEX
    Explanations

    Ajax or Touch requests

    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
    as
    -0.07
    atia
    -0.06
    aic
    -0.06
    atik
    -0.06
    tn
    -0.06
    èµĭåĢ¼
    -0.06
    绣ä¸Ģ社ä¼ļä¿¡çĶ¨ä»£çłģ
    -0.06
    vn
    -0.06
    ie
    -0.06
    å¤ļåħĥåĮĸ
    -0.06
    POSITIVE LOGITS
    stag
    0.08
    ¼Ī
    0.07
    [opt
    0.07
    è¶Ĭæĥ³
    0.07
    ogo
    0.07
    WindowTitle
    0.07
    ãĤ¦ãĥī
    0.07
    antino
    0.07
     déliv
    0.07
     ì§ĵ
    0.07
    Activations Density 0.242%

    No Known Activations