© 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. 21966
    Prev
    Next
    INDEX
    Explanations

    present invention

    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
     gì
    -0.08
    nam
    -0.08
    éĤ£è¾¹çļĦ
    -0.07
    çļĦèĥĮåIJİ
    -0.07
    æĤ¨å¥½
    -0.07
    ÙĨاÙĦ
    -0.07
    arani
    -0.07
    iple
    -0.07
    nai
    -0.07
    strap
    -0.07
    POSITIVE LOGITS
    oretical
    0.09
    -ci
    0.08
    ìłĢ
    0.08
    ×ļ
    0.07
    orem
    0.07
    redicate
    0.07
    kort
    0.07
    æīĢæĥ³
    0.07
    akening
    0.07
    ä¸įæ¯Ķ
    0.07
    Activations Density 0.039%

    No Known Activations