© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46747
    Prev
    Next
    INDEX
    Explanations

    not

    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
    çļĦéĿŀ
    -0.09
    ondon
    -0.08
    ä¸įåıª
    -0.08
     tartal
    -0.08
    reatest
    -0.08
    azer
    -0.08
    ELO
    -0.08
    almaz
    -0.08
    reichen
    -0.07
    tura
    -0.07
    POSITIVE LOGITS
     necessarily
    0.08
     ones
    0.08
     سÙĬÙħا
    0.07
    åįķ纯çļĦ
    0.07
     merely
    0.07
    .
    0.07
    缴æİ¥æĬĬ
    0.07
     sekadar
    0.07
     ÑģобÑģÑĤвенно
    0.06
    å®ĥéĤ£
    0.06
    Activations Density 0.029%

    No Known Activations