© 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. 22743
    Prev
    Next
    INDEX
    Explanations

    programming language constructs

    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
    romatic
    -0.06
    rio
    -0.06
    æij¸
    -0.06
    IONAL
    -0.06
    讲çļĦ
    -0.06
    b
    -0.06
     ë¹
    -0.06
    /assets
    -0.06
     Ant
    -0.06
    oen
    -0.05
    POSITIVE LOGITS
    å±Ĥ
    0.09
    åĢįå¢ŀ
    0.09
    ä¸Ģå±Ĥ
    0.08
    äºĮå±Ĥ
    0.08
     طبÙĤ
    0.08
    layer
    0.08
    åıĮå±Ĥ
    0.08
    ä¸Ģè·ĥ
    0.08
     Formation
    0.08
    两å±Ĥ
    0.08
    Activations Density 0.033%

    No Known Activations