© 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. 51141
    Prev
    Next
    INDEX
    Explanations

    according to the source

    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
    indsight
    -0.10
    clearfix
    -0.09
    illary
    -0.08
     nhÃłng
    -0.08
    irsch
    -0.08
    ëĭ¹íķľ
    -0.08
     noqa
    -0.08
    arnings
    -0.08
    æ¡ĤåĽŃ
    -0.08
     걸ì³IJ
    -0.07
    POSITIVE LOGITS
    emente
    0.09
    ees
    0.08
    ally
    0.08
    Ñıд
    0.08
    empa
    0.07
    hoz
    0.07
    é¢ĺæĦı
    0.07
    oppi
    0.07
    erve
    0.07
    äºİä¸ĸ
    0.07
    Activations Density 0.033%

    No Known Activations