© 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. 32751
    Prev
    Next
    INDEX
    Explanations

    cycles, structures, subsequences, or patterns formed

    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
     trickle
    -0.08
     Rojas
    -0.07
    款
    -0.07
    _exceptions
    -0.07
    èµ·å±ħ
    -0.07
     ballpark
    -0.07
    伶
    -0.07
     vall
    -0.06
    CustomAttributes
    -0.06
    æİ¥æīĭ
    -0.06
    POSITIVE LOGITS
     formed
    0.09
    formed
    0.08
    enuine
    0.08
     formations
    0.08
    æĪIJçīĩ
    0.07
     formation
    0.07
    åĽ¢ä¼Ļ
    0.07
    nets
    0.07
     consisting
    0.07
    secutive
    0.07
    Activations Density 0.010%

    No Known Activations