© 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. 18018
    Prev
    Next
    INDEX
    Explanations

    pneumatic, insulin, capecitabine, antibodies

    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
    วà¸ĩ
    -0.08
    ihad
    -0.08
    çĮ¿
    -0.07
    <|box_end|>
    -0.07
     tslib
    -0.07
    ë§IJë¡ľ
    -0.07
    cian
    -0.07
    दà¥įध
    -0.07
    ÅĤon
    -0.07
    é²ģ
    -0.07
    POSITIVE LOGITS
    iten
    0.06
    uts
    0.06
    athom
    0.06
    stuff
    0.06
    \/
    0.06
    ä¹ĭè¡Į
    0.06
     sot
    0.06
    itation
    0.06
     stuff
    0.06
    uty
    0.06
    Activations Density 0.673%

    No Known Activations