© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1717
    Prev
    Next
    INDEX
    Explanations

    overall excellent qualities

    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
    Not in Any Lists

    No Comments

    Negative Logits
    çļĦ带é¢Ĩ
    -0.32
    çļĦç¼ĺ
    -0.24
    figcaption
    -0.23
    åIJĦå¼ıåIJĦæł·
    -0.22
    optgroup
    -0.22
     Decompiled
    -0.22
    é»ijæģ¶
    -0.21
    æīĢæīĢ
    -0.21
    etchup
    -0.21
    çĸ¡
    -0.21
    POSITIVE LOGITS
     (!((
    0.27
    Overall
    0.25
     prostit
    0.24
    ä¼ĺç§Ģ
    0.24
     overall
    0.24
    çijķ
    0.23
     excellent
    0.23
    ç»Ļ人ä¸Ģç§į
    0.23
     qualities
    0.23
    å¹³åĿĩæ°´å¹³
    0.23
    Activations Density 4.616%

    No Known Activations