© 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. 42319
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ekar
    -0.08
    æīĵå¾Ĺ
    -0.07
    -track
    -0.07
    สุà¸Ļ
    -0.07
    olini
    -0.07
    çļĦçİ°å®ŀ
    -0.07
    ä¹ĭ忧
    -0.07
    uw
    -0.07
    éŨå¤ĸ
    -0.07
    utel
    -0.07
    POSITIVE LOGITS
    ©
    0.07
    escu
    0.07
    uba
    0.06
    ubl
    0.06
    strap
    0.06
    éĩijæĸ¯
    0.06
    insky
    0.06
    ya
    0.06
    äºĨä¸Ģè·³
    0.06
    rophic
    0.06
    Activations Density 0.000%

    No Known Activations