© 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. 28168
    Prev
    Next
    INDEX
    Explanations

    performance, nano, lithium, mechanical, transparency

    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
    æĹłåĬĽ
    -0.08
    大èĩ´
    -0.08
    ä»Ĭ天æĹ©ä¸Ĭ
    -0.07
    accia
    -0.07
     глÑİ
    -0.07
    hofer
    -0.07
     conting
    -0.07
    å½ĵå¹´
    -0.06
    âĹĭâĹĭ
    -0.06
     roughly
    -0.06
    POSITIVE LOGITS
    ä¸İä¼łç»Ł
    0.10
     optimized
    0.09
    仿çĶŁ
    0.09
    Nano
    0.09
     architectures
    0.09
     Nano
    0.09
    optimized
    0.09
     promising
    0.08
     nano
    0.08
    performance
    0.08
    Activations Density 0.446%

    No Known Activations