© 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. 32671
    Prev
    Next
    INDEX
    Explanations

    distinguishing between things

    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
    ä¸įæŃ£
    -0.07
    ikum
    -0.07
    çĤ¹æѤ
    -0.06
    azah
    -0.06
    å¸Ĥåľºè°ĥæŁ¥
    -0.06
    _some
    -0.06
    æķĻèģĮ
    -0.06
    ith
    -0.06
    /Gate
    -0.06
    zem
    -0.06
    POSITIVE LOGITS
     ÙĪبÙĬÙĨ
    0.10
    ä¸Ģç§įæĺ¯
    0.10
     illetve
    0.09
     sexes
    0.08
    ä½łè¿ĺæĺ¯
    0.08
    大åı¯
    0.08
    两ç§į
    0.08
    ëĥIJ
    0.08
    俨
    0.08
    è¿Ļ两ç§į
    0.08
    Activations Density 0.230%

    No Known Activations