© 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. 17226
    Prev
    Next
    INDEX
    Explanations

    part of

    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
    èĢĮå°±
    -0.10
    plorer
    -0.09
    ä¹ĭè¾Ī
    -0.09
    ়
    -0.09
    edelta
    -0.09
    ลà¹Į
    -0.09
    baugh
    -0.09
    erable
    -0.09
    arts
    -0.09
    oops
    -0.09
    POSITIVE LOGITS
    icularly
    0.11
    isans
    0.11
    icular
    0.10
    icipant
    0.10
     integrante
    0.10
    lessly
    0.09
    icipation
    0.09
    icip
    0.08
    iful
    0.08
    edly
    0.08
    Activations Density 0.094%

    No Known Activations