© 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. 18755
    Prev
    Next
    INDEX
    Explanations

    court documents and legal filings

    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
    ä¿®
    -0.06
    do
    -0.06
    ...
    -0.06
    éĺ³
    -0.06
    unkt
    -0.06
    izational
    -0.06
    eding
    -0.06
     обеÑĢ
    -0.06
    ijk
    -0.06
    X
    -0.06
    POSITIVE LOGITS
    åĩ³åŃIJ
    0.10
    æĢ¥äºĨ
    0.08
    ableView
    0.08
    æıIJä¾ĽæľĢ
    0.08
    quete
    0.08
    ilee
    0.08
     blat
    0.08
    FromClass
    0.08
     DataView
    0.08
    ä½ľåĪĻ
    0.08
    Activations Density 0.006%

    No Known Activations