© 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. 19620
    Prev
    Next
    INDEX
    Explanations

    dates and numerical sequences

    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
    ansa
    -0.08
    lang
    -0.08
    iš
    -0.08
    дÑĢе
    -0.08
    hent
    -0.07
    æİĮä¸Ĭ
    -0.07
    å°ıå²Ľ
    -0.07
    oje
    -0.07
    azan
    -0.07
     esclar
    -0.07
    POSITIVE LOGITS
    /archive
    0.07
    opsis
    0.07
    ocal
    0.07
    ÙģÙĪ
    0.07
    adium
    0.06
     pure
    0.06
    éĢŀ
    0.06
    å¤ĩæĪĺ
    0.06
     trump
    0.06
    æģ¤
    0.06
    Activations Density 0.118%

    No Known Activations