© 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. 57985
    Prev
    Next
    INDEX
    Explanations

    court document citation format

    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
    anni
    -0.08
    éĤĥ
    -0.07
    bauer
    -0.07
    PLIC
    -0.07
    ymar
    -0.07
    aira
    -0.07
     kÃŃnh
    -0.07
    æĻ®æ£®
    -0.07
    til
    -0.07
    é
    -0.07
    POSITIVE LOGITS
    è°¢ç»Ŀ
    0.07
    apot
    0.07
    åĮĤ
    0.06
    untime
    0.06
    éĻį
    0.06
     giò
    0.06
    æī§çºª
    0.06
    zol
    0.06
    è¿ĶåĽŀé¦ĸ页
    0.06
    fik
    0.06
    Activations Density 0.025%

    No Known Activations