© 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. 9808
    Prev
    Next
    INDEX
    Explanations

    mathematical or code expressions

    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
     atl
    -0.08
     Patterson
    -0.07
    datal
    -0.07
    ä¸ĵèģĮ
    -0.07
    ahari
    -0.07
    Tracks
    -0.06
    fran
    -0.06
    graded
    -0.06
    ycl
    -0.06
    _based
    -0.06
    POSITIVE LOGITS
     parentheses
    0.08
     concaten
    0.08
    éĩįéĩį
    0.08
    ngu
    0.08
    æĬĬå®ĥ们
    0.08
    æĬĬæīĢæľī
    0.07
    æŀĦéĢł
    0.07
    顺åºı
    0.07
    æĶĺ
    0.07
    éģĵéģĵ
    0.07
    Activations Density 0.012%

    No Known Activations