© 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. 51231
    Prev
    Next
    INDEX
    Explanations

    by or wise suffixes

    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
    çĿĢåĬĽçĤ¹
    -0.07
    ä¸Ģæİ¢
    -0.07
    ansen
    -0.07
    _INCLUDED
    -0.07
    ä¸ĢæıIJ
    -0.06
    大åĬŁ
    -0.06
     INTEG
    -0.06
    ]int
    -0.06
    ullah
    -0.06
     lév
    -0.06
    POSITIVE LOGITS
    nev
    0.08
    wise
    0.08
     từng
    0.08
    åħ¥å¾®
    0.07
    utsch
    0.07
    /unit
    0.07
    во
    0.07
    à¸Ĺัà¹Īว
    0.07
    ewise
    0.07
    -wise
    0.07
    Activations Density 0.006%

    No Known Activations