© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 4257
    Prev
    Next
    INDEX
    Explanations

    business operations

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    #Region
    -0.26
    å¾Īæ¼Ĥ亮
    -0.23
    :".$
    -0.23
     mktime
    -0.23
    acam
    -0.22
    ãİľ
    -0.22
        	č↵
    -0.21
    ĵĺ
    -0.21
    neapolis
    -0.21
    :NSLocalizedString
    -0.21
    POSITIVE LOGITS
    MouseButton
    0.23
     catchError
    0.21
    idency
    0.21
    buster
    0.21
    ä¼
    0.21
    usaha
    0.20
    æīĢ
    0.19
    -du
    0.19
    aines
    0.18
    ILTER
    0.18
    Activations Density 0.001%

    No Known Activations