© 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. 102
    Prev
    Next
    INDEX
    Explanations

    protection

    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
    rippling
    -0.47
    ocache
    -0.41
    esub
    -0.41
    oproject
    -0.40
    oplay
    -0.40
    odesk
    -0.40
    rades
    -0.39
    tsy
    -0.38
    aised
    -0.37
    oref
    -0.37
    POSITIVE LOGITS
    :')
    0.24
    ↵				↵
    0.24
     WIFI
    0.23
     présenté
    0.23
    ï¼ģï¼ģ↵↵
    0.23
     :</
    0.23
    åIJ¬è¯Ŀ
    0.23
    :';↵
    0.23
    ï¼Īç¬ij
    0.22
    æī«é»ij
    0.22
    Activations Density 9.724%

    No Known Activations