© 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. 47041
    Prev
    Next
    INDEX
    Explanations

    'th term', 'th term'

    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
    åIJĥåIJĥ
    -0.09
    arz
    -0.08
     Obser
    -0.07
    illos
    -0.07
    çİ°å®ŀ
    -0.07
    REE
    -0.07
    çİ°å®ŀçļĦ
    -0.07
    çIJĨæīĢ
    -0.07
    attery
    -0.07
    uling
    -0.07
    POSITIVE LOGITS
    untas
    0.07
    cak
    0.07
    表达å¼ı
    0.07
    plat
    0.06
    expr
    0.06
    åĤį
    0.06
    æĭīå¾·
    0.06
     expressions
    0.06
    ç¹ģèį£æĺĮ缼
    0.06
    lef
    0.06
    Activations Density 0.010%

    No Known Activations