© 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. 16664
    Prev
    Next
    INDEX
    Explanations

    legal documents and texts

    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
    ezo
    -0.08
    WithTag
    -0.08
    æĸ¹æ³ķæĺ¯
    -0.07
    routine
    -0.07
    çļĦæīĢæľīä½ľåĵģ
    -0.07
    _methods
    -0.07
    elihood
    -0.07
     Fazenda
    -0.07
    ntag
    -0.07
     Bretagne
    -0.07
    POSITIVE LOGITS
    èįīæ¡Ī
    0.11
    é¢ģå¸ĥ
    0.10
    à¸īà¸ļัà¸ļ
    0.10
    ä¿®æŃ£æ¡Ī
    0.10
    åĩºçĤī
    0.09
    修订
    0.09
     amendments
    0.09
     defining
    0.08
    åħ¸
    0.08
     governing
    0.08
    Activations Density 0.139%

    No Known Activations