© 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. 3341
    Prev
    Next
    INDEX
    Explanations

    programming context keywords

    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
    ono
    -0.07
    ross
    -0.06
    pa
    -0.06
    ¬
    -0.06
    æ½ĩæ¹ĺ
    -0.06
    ج
    -0.05
     i
    -0.05
    ails
    -0.05
    iating
    -0.05
     pa
    -0.05
    POSITIVE LOGITS
    .AP
    0.08
    awi
    0.08
    EventManager
    0.08
    боÑİ
    0.07
    λÏİ
    0.07
    brem
    0.07
    ×Ĺ×Ļ
    0.07
    ì¶ĺ
    0.07
    abis
    0.07
    trap
    0.07
    Activations Density 0.052%

    No Known Activations