© 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. 32048
    Prev
    Next
    INDEX
    Explanations

    neoadjuvant therapy or legislative assembly

    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
    æıIJ
    -0.06
     totiž
    -0.06
    åİĺ
    -0.06
    S
    -0.06
    èĤ¥èĤī
    -0.06
    -
    -0.06
    è¸
    -0.05
    èĩ´
    -0.05
    CM
    -0.05
    æĿIJ
    -0.05
    POSITIVE LOGITS
    æĤ¨å½ĵåīįçļĦä½įç½®
    0.10
    apas
    0.09
    NewItem
    0.08
    itest
    0.08
    ActionCode
    0.08
    onte
    0.08
    ForObject
    0.08
    æľ¬ç«ĻåĨħ容
    0.08
    ä¹Łåı¯ä»¥æĺ¯
    0.08
    ertas
    0.08
    Activations Density 0.287%

    No Known Activations