© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22759
    Prev
    Next
    INDEX
    Explanations

    numbers followed by characters

    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
    ieden
    -0.07
     dim
    -0.07
    à¬Ľ
    -0.07
    orman
    -0.07
    åĩ«
    -0.06
    ä¸Ģåĵģ
    -0.06
    å·²ç»ıå®ĮæĪIJ
    -0.06
    à¯įà®Ł
    -0.06
    -ignore
    -0.06
    misc
    -0.06
    POSITIVE LOGITS
    ä¹ĭæĺŁ
    0.07
    üle
    0.06
    _closure
    0.06
    åĵī
    0.06
    isd
    0.06
    adiyah
    0.06
    åĺĺ
    0.06
     Gund
    0.06
    ywa
    0.06
    ilon
    0.06
    Activations Density 0.017%

    No Known Activations