© 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. 15235
    Prev
    Next
    INDEX
    Explanations

    -associated, -dependent, -induced, -related terms

    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
    ì§ĵ
    -0.07
    大èĢĮ
    -0.06
    et
    -0.06
    ant
    -0.06
    å½¹
    -0.06
    en
    -0.06
    æİ
    -0.06
    笳
    -0.06
    im
    -0.06
    unk
    -0.05
    POSITIVE LOGITS
    zing
    0.09
    第ä¸Ģ人
    0.08
    swire
    0.08
    adesh
    0.08
    ÙĪÙĬب
    0.08
    обен
    0.08
    ллÑı
    0.08
    оеди
    0.08
    ä¸İçİ°å®ŀ
    0.08
    ¬´
    0.08
    Activations Density 0.227%

    No Known Activations