© 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. 42737
    Prev
    Next
    INDEX
    Explanations

    mediated / related / based

    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
    emente
    -0.08
    ়
    -0.06
    ional
    -0.06
    ÑģлÑĮ
    -0.06
    iciencies
    -0.06
    çļĦä¸ĢçĤ¹
    -0.06
    iable
    -0.06
    ä¹ĭåIJİ
    -0.06
    ä¹ĭ为
    -0.06
    -ish
    -0.06
    POSITIVE LOGITS
    er
    0.11
    gether
    0.10
    à¹Į
    0.09
    hoc
    0.09
    suite
    0.09
    داÙĨ
    0.08
    cident
    0.08
    /proto
    0.08
    mite
    0.08
    erb
    0.08
    Activations Density 0.030%

    No Known Activations