© 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. 12517
    Prev
    Next
    INDEX
    Explanations

    versus

    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
    ÏĨÎŃÏģει
    -0.07
    ÏĨεÏģ
    -0.06
    èIJ½äºĨ
    -0.06
    ovina
    -0.06
    çĥŃéŨæݨèįIJ
    -0.06
    馴
    -0.06
    æī£äººå¿ĥ弦
    -0.06
    /activity
    -0.06
     interp
    -0.06
    सà¥įता
    -0.06
    POSITIVE LOGITS
    _vs
    0.08
     vs
    0.08
    ä½ľä¸ºä¸Ģç§į
    0.07
    å½Ĵå±ŀäºİ
    0.07
     versus
    0.07
    åģļ为
    0.06
     ë¹Ħ롯íķľ
    0.06
    eke
    0.06
     compared
    0.06
    ä½ľä¸º
    0.06
    Activations Density 0.650%

    No Known Activations