© 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. 20484
    Prev
    Next
    INDEX
    Explanations

    reputation

    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
     kupon
    -0.08
    ermen
    -0.07
    tagne
    -0.07
    ippers
    -0.07
    uction
    -0.07
    erman
    -0.07
    lude
    -0.07
    å½¢å¼ıå¤ļæł·çļĦ
    -0.07
    meal
    -0.07
    ÑĤалÑĮÑı
    -0.07
    POSITIVE LOGITS
    ä¸įä½³
    0.08
     quo
    0.07
    izen
    0.07
     itib
    0.07
    åı£ç¢ij
    0.07
    èĢģåºĹ
    0.07
    åĴĮç»ıéªĮ
    0.07
    æī¬æī¬
    0.07
    icky
    0.07
    hani
    0.07
    Activations Density 0.036%

    No Known Activations