© 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. 51164
    Prev
    Next
    INDEX
    Explanations

    French titles and authorship

    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
     whilst
    -0.08
    Whilst
    -0.08
     Whilst
    -0.08
     firstly
    -0.08
     Firstly
    -0.08
    ä»Ĭ次
    -0.07
     stet
    -0.06
    _plain
    -0.06
    ר×ķת
    -0.06
     alright
    -0.06
    POSITIVE LOGITS
     travelers
    0.08
    ÏĦÏģÏĮ
    0.08
    请æĭ¨æīĵ
    0.08
     condu
    0.08
    วย
    0.08
    ansir
    0.07
    .rawValue
    0.07
     destin
    0.07
    æ´ģåħ·
    0.07
    æĢ»ä½ĵè§ĦåĪĴ
    0.07
    Activations Density 0.018%

    No Known Activations