© 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. 11657
    Prev
    Next
    INDEX
    Explanations

    Squadron

    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
    åķ¸
    -0.07
    θÎŃ
    -0.07
    eenth
    -0.07
    izon
    -0.07
    atoon
    -0.07
    emean
    -0.07
    zman
    -0.07
    è¿ĽåĪ¶
    -0.07
    anus
    -0.07
    å¤ĦçIJĨçļĦ
    -0.07
    POSITIVE LOGITS
    alej
    0.07
    pper
    0.07
    วà¸ĩ
    0.07
    æľ¬ä½ľ
    0.07
    亲åĴĮ
    0.07
    家æľī
    0.07
    æĺ
    0.07
    /API
    0.06
     Gug
    0.06
    itzer
    0.06
    Activations Density 0.001%

    No Known Activations