© 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. 30871
    Prev
    Next
    INDEX
    Explanations

    scientific and medical 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
    avais
    -0.09
    ç¾¹
    -0.08
    odaw
    -0.08
    ials
    -0.08
    ificate
    -0.08
    Ajax
    -0.08
    é£Ł
    -0.08
    upert
    -0.07
    ophone
    -0.07
    íݸ
    -0.07
    POSITIVE LOGITS
     Rund
    0.07
    åħµçİĭ
    0.06
    çī¹èѦ
    0.06
    ä¹ĭåIJį
    0.06
     intending
    0.06
    大åĴĸ
    0.06
    ä¸İçĶŁæ´»
    0.06
     potent
    0.06
     Lover
    0.06
    è·Ĩ
    0.06
    Activations Density 0.105%

    No Known Activations