© 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. 1819
    Prev
    Next
    INDEX
    Explanations

    web or code links

    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
    çļĦç¼ĺ
    -0.30
    äºĨ好å¤ļ
    -0.26
    çļĦæ¨¡æł·
    -0.25
    äºĨ好åĩł
    -0.25
    æľīæĦıæĢĿçļĦ
    -0.25
    çļĦ带é¢Ĩ
    -0.24
    ürn
    -0.24
    åľ¨çݩ家
    -0.23
    çļĦéĤ£ç§į
    -0.23
    ppard
    -0.23
    POSITIVE LOGITS
     Dems
    0.26
    ÑĥниÑĨип
    0.23
     Según
    0.23
    迨
    0.23
     -------------------------------------------------------------------------
    0.22
     intox
    0.21
     Vimeo
    0.20
     Después
    0.20
    åĹĿ
    0.19
    -scalable
    0.19
    Activations Density 2.057%

    No Known Activations