© 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. 10285
    Prev
    Next
    INDEX
    Explanations

    citing sources or authors

    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
    rag
    -0.08
    ()].
    -0.08
    geries
    -0.07
    tdown
    -0.07
    åĩºäºº
    -0.07
    åĽŀåĪ°äºĨ
    -0.07
    å¤įåĪ¶æĪĸ
    -0.07
    ÅĽciÄħ
    -0.07
    PlainText
    -0.07
    ))->
    -0.07
    POSITIVE LOGITS
    гÑĢан
    0.06
    ç¢į
    0.06
    áro
    0.06
    ear
    0.06
    ç»ĻæĪijçķĻè¨Ģ
    0.06
    ize
    0.06
     ado
    0.06
     Kore
    0.06
    stes
    0.06
    (zip
    0.06
    Activations Density 0.022%

    No Known Activations