© 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. 58611
    Prev
    Next
    INDEX
    Explanations

    numbers and percentages

    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
     \"{
    -0.08
     Woh
    -0.08
    itto
    -0.07
    ازÙĦ
    -0.07
    isnan
    -0.07
    chst
    -0.07
    _UNSIGNED
    -0.07
    enda
    -0.07
    é«ĺæĺİ
    -0.07
    æľīç¦ı
    -0.07
    POSITIVE LOGITS
    ÙģاÙĤ
    0.07
    rael
    0.07
    avel
    0.07
    линг
    0.06
    æł¸åıij
    0.06
     mos
    0.06
    conse
    0.06
    ç±³å°Ķ
    0.06
    appen
    0.06
    abs
    0.06
    Activations Density 0.002%

    No Known Activations