© 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. 61850
    Prev
    Next
    INDEX
    Explanations

    focus on specific tasks or aspects

    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
    iho
    -0.09
    زاÙħ
    -0.08
    odos
    -0.08
    ODO
    -0.08
    iel
    -0.07
    缨
    -0.07
    /perl
    -0.07
    arus
    -0.07
    ç«ĭåį³
    -0.07
    ieli
    -0.07
    POSITIVE LOGITS
     focus
    0.10
    ä¸ĵ注äºİ
    0.10
    羣æŃ£
    0.09
    ä¸ĵå¿ĥ
    0.09
     focused
    0.09
     focusing
    0.09
     genuine
    0.09
    éĽĨä¸Ńç²¾åĬĽ
    0.08
    æľ¬æĿ¥
    0.08
     fokus
    0.08
    Activations Density 0.145%

    No Known Activations