© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46737
    Prev
    Next
    INDEX
    Explanations

    is a condition

    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
    itz
    -0.07
     dor
    -0.06
    çĶ¨æľĢ
    -0.06
    zeÅĦ
    -0.06
    迸
    -0.06
    ×Ļ×Ļ×Ŀ
    -0.06
    à¹Īà¸ĩ
    -0.05
    ¹
    -0.05
    æĿİå°ı
    -0.05
    ¢
    -0.05
    POSITIVE LOGITS
    pery
    0.10
    eka
    0.08
    ÙĦاØŃ
    0.08
    é·¹
    0.08
    apr
    0.08
    anny
    0.08
    راÙĤ
    0.08
    mith
    0.08
    ety
    0.08
    鼼
    0.08
    Activations Density 0.034%

    No Known Activations