© 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. 65280
    Prev
    Next
    INDEX
    Explanations

    Slovenia

    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
    èĤĨ
    -0.07
    ays
    -0.07
    ми
    -0.06
    OnClick
    -0.06
     pie
    -0.06
    çļĦæĿIJæĸĻ
    -0.06
     ActiveSupport
    -0.06
     whereas
    -0.06
    aid
    -0.06
    d
    -0.06
    POSITIVE LOGITS
    åĪĨ许
    0.09
    toor
    0.08
    appa
    0.08
    ÎŃλ
    0.08
     runApp
    0.08
    ictured
    0.08
    िति
    0.08
    subcategory
    0.08
    extract
    0.08
    ocene
    0.08
    Activations Density 0.006%

    No Known Activations