© 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. 33804
    Prev
    Next
    INDEX
    Explanations

    form, exclamation, bold, linked, select

    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
    ringer
    -0.07
    ungan
    -0.07
    rapper
    -0.06
    åİĨåı²ä¸Ĭ
    -0.06
    é»ĺ
    -0.06
    åĮ¿
    -0.06
    haben
    -0.06
    æĹ¥æ¸¸
    -0.06
    edata
    -0.06
    没æľīåħ¶ä»ĸ
    -0.06
    POSITIVE LOGITS
     whenever
    0.09
    apak
    0.08
    Whenever
    0.08
    uko
    0.07
    à¸ļà¹īาà¸ĩ
    0.07
    enges
    0.07
    åīįèĮħ
    0.07
    à´·
    0.07
     wherever
    0.07
     Whenever
    0.07
    Activations Density 0.004%

    No Known Activations