© 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. 47788
    Prev
    Next
    INDEX
    Explanations

    initialisms and abbreviations

    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
     sekadar
    -0.08
    erweise
    -0.08
    asiun
    -0.08
     sekedar
    -0.07
    ضاÙĨ
    -0.07
    à®°à¯Ī
    -0.07
     sheer
    -0.07
     sfida
    -0.07
    ÑĪева
    -0.07
    à´´
    -0.07
    POSITIVE LOGITS
    (sh
    0.14
    pherd
    0.12
    ftware
    0.10
    apiro
    0.10
    neider
    0.10
    ffield
    0.10
    ewart
    0.10
    tlement
    0.10
    uttgart
    0.10
     hãi
    0.09
    Activations Density 4.767%

    No Known Activations