© 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. 500
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    -Speed
    -0.29
     Xperia
    -0.27
     nouve
    -0.25
     vidé
    -0.25
     ila
    -0.24
    gnore
    -0.24
    malink
    -0.23
    uyá»ĥn
    -0.23
    unfinished
    -0.23
     prostitu
    -0.23
    POSITIVE LOGITS
    rippling
    0.32
    CLUDING
    0.27
    enuity
    0.26
    extérieur
    0.23
    urrenc
    0.22
    åIJĮå¿Ĺ们
    0.22
    earable
    0.22
    écoute
    0.22
    ritis
    0.21
    ERSHEY
    0.21
    Activations Density 1.185%

    No Known Activations