© 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. 33489
    Prev
    Next
    INDEX
    Explanations

    part of

    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
    ç´ł
    -0.07
    ynu
    -0.07
    wei
    -0.07
    ESH
    -0.07
     ì¶ľìĭł
    -0.07
    sei
    -0.07
    æŶéĹ´ä¸İ
    -0.07
    xCE
    -0.06
    ads
    -0.06
    ัà¸Ķ
    -0.06
    POSITIVE LOGITS
    æĢ»çļĦ
    0.10
     broader
    0.09
     overall
    0.09
     Gesamt
    0.09
     Gesam
    0.08
    overall
    0.08
    orsa
    0.08
    çļĦæķ´ä½ĵ
    0.08
    æĢ»ä½ĵ
    0.08
    ä½ĵç³»
    0.08
    Activations Density 0.558%

    No Known Activations