© 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. 47661
    Prev
    Next
    INDEX
    Explanations

    Eastern European names or suffixes

    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»¬åľ¨
    -0.09
    们
    -0.08
    .nasa
    -0.08
     Golk
    -0.08
    atur
    -0.07
     ...\
    -0.07
    antar
    -0.07
    ä»¬ä¹Ł
    -0.07
    oooooooo
    -0.07
    urgi
    -0.07
    POSITIVE LOGITS
    dyn
    0.06
     aka
    0.06
    ãģ®ãĤĤãģ¨
    0.06
    ç¬ĶåIJį
    0.06
    division
    0.06
    âĢİ
    0.06
     blunt
    0.06
    0.05
     ØŃد
    0.05
    ловиÑĩ
    0.05
    Activations Density 0.657%

    No Known Activations