© 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. 1750
    Prev
    Next
    INDEX
    Explanations

    License

    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
    èµ·çłģ
    -0.22
    ();++
    -0.22
    æī«é»ij
    -0.22
    åĽ½æĥħ
    -0.22
    åĬĦ
    -0.21
     &);↵
    -0.20
    ç§ijåѦéĻ¢
    -0.19
     mé
    -0.19
     jä
    -0.18
    	throws
    -0.18
    POSITIVE LOGITS
    -Identifier
    0.25
    pisa
    0.24
    mdat
    0.23
    rende
    0.23
    ]='\
    0.23
    printStats
    0.22
    enery
    0.21
    reten
    0.21
    agas
    0.20
    curacy
    0.20
    Activations Density 1.957%

    No Known Activations