© 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. 15554
    Prev
    Next
    INDEX
    Explanations

    nested loops

    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
    heimer
    -0.08
    aser
    -0.08
    ÄĻcz
    -0.07
    æµ·åĮº
    -0.07
    serialized
    -0.07
    çİĦå¾·
    -0.07
    veni
    -0.07
    èįŁèIJĥ
    -0.07
    unders
    -0.06
    çek
    -0.06
    POSITIVE LOGITS
    "]))
    0.07
    ç´§éļı
    0.06
    getVar
    0.06
    深度
    0.06
    omin
    0.06
    utsal
    0.06
    wick
    0.06
    MSG
    0.06
    太éĥİ
    0.06
    eco
    0.06
    Activations Density 0.027%

    No Known Activations