© 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. 49557
    Prev
    Next
    INDEX
    Explanations

    type identifiers and specific terms

    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
    èĴĤ
    -0.08
    ä»İåīį
    -0.08
    ืà¸Ńà¸ĩ
    -0.07
    ovina
    -0.07
    дем
    -0.07
    à¸ģำ
    -0.07
    ievi
    -0.07
    ä»İåݻ年
    -0.07
    天æĪIJ
    -0.07
    dsn
    -0.07
    POSITIVE LOGITS
    æĦ
    0.07
     pa
    0.06
     entr
    0.06
    brace
    0.06
    _inline
    0.06
    ]
    0.06
    责任åĴĮ
    0.06
    ãĢıãĢİ
    0.06
    "][
    0.06
    alian
    0.06
    Activations Density 0.229%

    No Known Activations