© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46432
    Prev
    Next
    INDEX
    Explanations

    account maintenance cannabis order

    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
    olec
    -0.08
    å¸ĥæŀĹ
    -0.08
    -equiv
    -0.08
    çĮªèĤĿ
    -0.07
    opensource
    -0.07
    hirt
    -0.07
    _typeof
    -0.07
    ×Ĵ×¢
    -0.07
    orden
    -0.07
    upil
    -0.07
    POSITIVE LOGITS
    æŁIJäºĽ
    0.08
    åľ¨æŁIJäºĽ
    0.08
    å¥ĩ
    0.07
    atisation
    0.06
     some
    0.06
    Help
    0.06
    aris
    0.06
    积
    0.06
     sometimes
    0.06
    æŁIJç§įç¨ĭ度ä¸Ĭ
    0.06
    Activations Density 0.359%

    No Known Activations