© 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. 19640
    Prev
    Next
    INDEX
    Explanations

    diffusion coefficient

    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
    urai
    -0.07
    nant
    -0.07
    å°Ķå¤ļ
    -0.06
    éľ¹éĽ³
    -0.06
    _MALLOC
    -0.06
    ä»ĺæ¸ħ
    -0.06
    åĭĴç´¢
    -0.06
     toll
    -0.06
    解éĻ¤
    -0.06
     slate
    -0.06
    POSITIVE LOGITS
    æī©æķ£
    0.11
     diffusion
    0.09
    å¾Īæħ¢
    0.09
     speeds
    0.09
     sluggish
    0.09
    è¶Ĭå¿«
    0.09
     fastest
    0.09
    éĢŁçİĩ
    0.09
    transport
    0.09
    adius
    0.08
    Activations Density 0.010%

    No Known Activations