© 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. 7867
    Prev
    Next
    INDEX
    Explanations

    SQL connection strings

    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
    houd
    -0.08
    alie
    -0.07
    nst
    -0.07
    اÙĦÙĬا
    -0.07
    اÙħÙĬØ©
    -0.07
    ibold
    -0.07
     Recu
    -0.07
    indel
    -0.07
    esai
    -0.07
    forward
    -0.06
    POSITIVE LOGITS
    ãģĹãģ®
    0.07
    ç¥ŀä¹ĭ
    0.07
    ings
    0.07
    .compress
    0.07
     Harr
    0.06
    ãģªãģĮãĤī
    0.06
    iens
    0.06
    ikas
    0.06
    γÏĩ
    0.06
    大潮
    0.06
    Activations Density 0.109%

    No Known Activations