© 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. 55840
    Prev
    Next
    INDEX
    Explanations

    `_matrix` after `uson`

    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
    angu
    -0.07
    åĿ¦
    -0.06
     State
    -0.06
    åĽŀçŃĶéĹ®é¢ĺ
    -0.06
    ä¸ĸçķĮ级
    -0.06
    ä½ľçŃĶ
    -0.06
     baff
    -0.06
    essim
    -0.06
    wski
    -0.06
    eb
    -0.06
    POSITIVE LOGITS
    ikle
    0.09
    ắc
    0.09
    jør
    0.08
     Ilmais
    0.08
    rito
    0.08
    herits
    0.08
     cellspacing
    0.08
    ITO
    0.08
    á»Ļt
    0.08
    ÙĤبÙĦ
    0.08
    Activations Density 0.001%

    No Known Activations