© 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. 14399
    Prev
    Next
    INDEX
    Explanations

    task or problem description

    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
    )?
    -0.08
     anything
    -0.08
    [".
    -0.07
    parency
    -0.07
    ä¸Ģ带
    -0.07
     angk
    -0.07
    elper
    -0.07
    åIJĦèĩªçļĦ
    -0.07
    ä¸Ģ帶
    -0.07
     everything
    -0.07
    POSITIVE LOGITS
    åĴĮä¸Ģ个
    0.07
    åĮĸçļĦ
    0.07
    åĴĮä¸ĢäºĽ
    0.07
    rawn
    0.06
    ç¬
    0.06
    åĩ¡
    0.06
    èģĶ缣
    0.06
    udi
    0.06
     consisting
    0.06
    itto
    0.06
    Activations Density 0.091%

    No Known Activations