© 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. 40689
    Prev
    Next
    INDEX
    Explanations

    .io games, strings, dates

    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
    fc
    -0.06
    á»Ŀ
    -0.06
    积åİĭ
    -0.06
    åĩºç«Ļ
    -0.06
    terr
    -0.06
     alum
    -0.06
     аккÑĥмÑĥлÑı
    -0.06
     grave
    -0.06
    åѤç«ĭ
    -0.06
     throwable
    -0.06
    POSITIVE LOGITS
    atra
    0.09
    agal
    0.09
    ambu
    0.09
    pont
    0.08
     tension
    0.08
    curl
    0.08
    VML
    0.08
    碳纤维
    0.08
    æ¡¥
    0.08
    betes
    0.08
    Activations Density 0.006%

    No Known Activations