© 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. 25737
    Prev
    Next
    INDEX
    Explanations

    Khovanova

    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
    jem
    -0.07
    latin
    -0.07
    lrt
    -0.07
    uede
    -0.07
    sev
    -0.07
    fw
    -0.06
    geois
    -0.06
    ئÛĴ
    -0.06
    gu
    -0.06
    aaa
    -0.06
    POSITIVE LOGITS
    åĸ¶
    0.08
    undur
    0.08
    Æ¡n
    0.08
    kü
    0.08
    éĩijåĪ¸
    0.07
    å¼ģ
    0.07
    áĢĢáĢº
    0.07
    循
    0.07
    称
    0.07
    CF
    0.07
    Activations Density 0.011%

    No Known Activations