© 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. 32643
    Prev
    Next
    INDEX
    Explanations

    list enumeration

    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
    å¾Ī
    -0.07
    ÙĪاÙĨ
    -0.07
    aurus
    -0.07
    afx
    -0.07
    weif
    -0.07
    egos
    -0.06
    ש×Ķ
    -0.06
    indsight
    -0.06
    tridge
    -0.06
    Ø·
    -0.06
    POSITIVE LOGITS
    ä¸Ģæĺ¯
    0.09
    ä¹Łæĺ¯æľĢ
    0.08
     Firstly
    0.08
     اÛĮÙĨÚ©Ùĩ
    0.08
    teres
    0.08
    å³¥
    0.08
    ARP
    0.07
    ìłĪ
    0.07
    »
    0.07
    ï¸ı
    0.07
    Activations Density 0.338%

    No Known Activations