© 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. 31175
    Prev
    Next
    INDEX
    Explanations

    functional properties of systems

    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
    æĪĸ以åħ¶ä»ĸæĸ¹å¼ı
    -0.09
    umis
    -0.08
    fér
    -0.08
    wich
    -0.08
    sWith
    -0.08
    gettext
    -0.08
    åıĬåħ¶åºĶçĶ¨
    -0.08
    تÙĪÙĨ
    -0.08
    mux
    -0.08
    adium
    -0.07
    POSITIVE LOGITS
     berupa
    0.09
     regarding
    0.08
     poleg
    0.07
    åį³åľ¨
    0.07
     hinsichtlich
    0.07
    åį³çĶ¨
    0.06
     bezüglich
    0.06
    ä¸įåłª
    0.06
    ä¹ĭä¸Ģå°±æĺ¯
    0.06
     dah
    0.06
    Activations Density 0.598%

    No Known Activations