© 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. 42976
    Prev
    Next
    INDEX
    Explanations

    introduction section field

    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
    ago
    -0.06
    ith
    -0.06
    udi
    -0.05
     Amar
    -0.05
     F
    -0.05
    宿åij½
    -0.05
    å§Ķ
    -0.05
    èݹ
    -0.05
     dynam
    -0.05
    -0.05
    POSITIVE LOGITS
     ngã
    0.09
    _SECTION
    0.09
    [section
    0.08
    ÏģοÏį
    0.08
    _SYN
    0.08
    第ä¸ĢèĬĤ
    0.08
    çļĦçģµéŃĤ
    0.08
     prelimin
    0.08
    解åĨ³éĹ®é¢ĺçļĦ
    0.08
    ä¹ĭçİĭ
    0.08
    Activations Density 0.228%

    No Known Activations