© 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. 3264
    Prev
    Next
    INDEX
    Explanations

    [@ citation marker]

    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
     preferably
    -0.06
     EITHER
    -0.06
    å°½éĩı
    -0.06
    (
    -0.06
     lazy
    -0.06
    æľĢåħ¨
    -0.06
    `
    -0.06
    æľĢ好
    -0.06
    æľĢç¾İçļĦ
    -0.06
    æľĢæľĢ
    -0.06
    POSITIVE LOGITS
    ppelin
    0.08
    odox
    0.08
    ¿IJ
    0.08
    tti
    0.08
    IFI
    0.08
    inander
    0.08
    μά
    0.08
    ä¹IJä¹İ
    0.08
    comings
    0.08
    otella
    0.08
    Activations Density 0.064%

    No Known Activations