© 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. 4479
    Prev
    Next
    INDEX
    Explanations

    code comments or punctuation

    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
    佬
    -0.07
    æĤ¬å´ĸ
    -0.07
    fad
    -0.07
    oni
    -0.07
    one
    -0.06
    _cb
    -0.06
     provision
    -0.06
    à¸Ĺี
    -0.06
    loe
    -0.06
    iliate
    -0.06
    POSITIVE LOGITS
    artet
    0.08
    abinet
    0.07
    ignan
    0.07
    ansson
    0.07
    __/
    0.07
    éģ¨
    0.07
    estring
    0.07
    anny
    0.07
     sâm
    0.06
    oret
    0.06
    Activations Density 0.005%

    No Known Activations