© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3643
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     ['
    -0.22
     '
    -0.21
    pond
    -0.20
    ,
    -0.20
    æ´Į
    -0.19
    uards
    -0.19
    åĸ³
    -0.19
    ['
    -0.19
    apon
    -0.19
    beth
    -0.18
    POSITIVE LOGITS
    -Mobile
    0.22
    Č↵
    0.22
    indent
    0.21
     ×Ķ×ķ×ĵ
    0.20
    plen
    0.20
    opportunitÃł
    0.20
    alist
    0.20
    leine
    0.20
    -Headers
    0.19
    inputEmail
    0.19
    Activations Density 0.058%

    No Known Activations