© 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. 23495
    Prev
    Next
    INDEX
    Explanations

    easy to

    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
    累累
    -0.10
    并èĮĤ
    -0.09
    å¦Ĥä¸Ģ
    -0.08
    /cop
    -0.08
    à¸ģรรม
    -0.08
    ä¸įæĩĪåĬªåĬĽ
    -0.08
    好好åŃ¦ä¹ł
    -0.08
    плей
    -0.08
    icoli
    -0.08
    icola
    -0.08
    POSITIVE LOGITS
     dÃłng
    0.18
    ly
    0.10
    est
    0.10
    -minded
    0.09
     enough
    0.09
    ä¸Ĭæīĭ
    0.08
    容æĺĵ
    0.08
    ened
    0.08
    æĺĵ
    0.08
     جداÙĭ
    0.08
    Activations Density 0.058%

    No Known Activations