© 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. 26196
    Prev
    Next
    INDEX
    Explanations

    code and formulas

    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
    aat
    -0.07
    åīĶéĢı
    -0.07
    ØŃاÙħ
    -0.07
    o
    -0.07
    å°ıäºĭ
    -0.07
    è¡£è£Ļ
    -0.06
     à¹Ĩ
    -0.06
    çļĦäºĭæĥħäºĨ
    -0.06
    иб
    -0.06
     siis
    -0.06
    POSITIVE LOGITS
    zee
    0.09
    Äĥn
    0.08
    çļĦ
    0.08
    ÙģÙĨ
    0.07
    BTN
    0.07
    elsius
    0.07
     equ
    0.06
    à¸Ńà¸Ĺ
    0.06
    opcion
    0.06
    icker
    0.06
    Activations Density 0.003%

    No Known Activations