© 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. 56434
    Prev
    Next
    INDEX
    Explanations

    information about

    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
    segn
    -0.07
    ersh
    -0.07
    tock
    -0.07
    è¢ħ
    -0.07
    hing
    -0.07
    çĶ²çĬ¶
    -0.07
    æ¯Ķä¾ĭçļĦ
    -0.07
    å¿ĥå¾Ĺ
    -0.07
    kende
    -0.07
    ToLocal
    -0.07
    POSITIVE LOGITS
    æ»Ķ
    0.07
    ostar
    0.07
    ÙĬد
    0.07
    è¢Ń
    0.07
    s
    0.07
    pin
    0.06
    æµ·æ³¢
    0.06
    /material
    0.06
    surf
    0.06
    èvre
    0.06
    Activations Density 0.001%

    No Known Activations