© 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. 40241
    Prev
    Next
    INDEX
    Explanations

    original content/descriptions

    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
    æĸ°æĬĢæľ¯
    -0.08
    æĸ°çļĦ
    -0.08
    å½ĵåīįçļĦ
    -0.07
    esian
    -0.07
    å®ĥä¸İ
    -0.06
    bye
    -0.06
    antis
    -0.06
    elsey
    -0.06
    çŁŃ线
    -0.06
    à¸Ńà¸Ł
    -0.06
    POSITIVE LOGITS
    /original
    0.13
     original
    0.10
    åİŁ
    0.10
    original
    0.10
     originale
    0.10
     originalmente
    0.09
     originally
    0.09
     ìĽIJëŀĺ
    0.09
     Original
    0.09
    (original
    0.09
    Activations Density 0.034%

    No Known Activations