© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26851
    Prev
    Next
    INDEX
    Explanations

    wxPython, syndrome, transit commuter, red blood cells, retinitis pigmentosa

    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
    opp
    -0.06
    ´
    -0.06
    è¾ľ
    -0.06
    g
    -0.06
     respectively
    -0.06
    KE
    -0.06
     Guerrero
    -0.06
    åľ¨éĤ£éĩĮ
    -0.06
    ising
    -0.06
    æĺ¯æĮĩ
    -0.06
    POSITIVE LOGITS
    ä¹Łä¸įä¾ĭå¤ĸ
    0.09
    ONGL
    0.09
    ajem
    0.08
    ,__
    0.08
    rze
    0.08
    ISTI
    0.08
    ä¹Łæĺ¯ä¸Ģæł·
    0.08
    etim
    0.08
    ÏĦει
    0.08
    ìŀ
    0.08
    Activations Density 0.008%

    No Known Activations