© 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. 15664
    Prev
    Next
    INDEX
    Explanations

    preposition or conjunction followed by noun

    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
    aday
    -0.09
    olat
    -0.07
    oon
    -0.07
    ight
    -0.07
    mekte
    -0.07
    éķ¿æĮīè¯ĨåĪ«äºĮç»´çłģ
    -0.06
    ayet
    -0.06
    owitz
    -0.06
    aku
    -0.06
    opard
    -0.06
    POSITIVE LOGITS
     mixed
    0.08
    ä½ľå¥½
    0.07
    ､
    0.07
    à¸Ńม
    0.07
    æľīæĿ¡ä»¶
    0.07
    å®ĮæĪIJä»»åĬ¡
    0.07
    ócz
    0.07
    )")
    0.07
    (Tag
    0.07
    åºŀ
    0.07
    Activations Density 0.080%

    No Known Activations