© 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. 3896
    Prev
    Next
    INDEX
    Explanations

    technical or scientific

    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
    \OptionsResolver
    -0.21
    scriber
    -0.19
    çĹĶ
    -0.19
    lland
    -0.19
     Snyder
    -0.19
    NOWLED
    -0.19
    unsch
    -0.18
    etter
    -0.18
    ç½ijé¦ĸ页
    -0.18
    utherland
    -0.18
    POSITIVE LOGITS
    adj
    0.22
    èįŃ
    0.20
     numberWith
    0.19
    ï½Ģ
    0.19
    .navigate
    0.19
    æĿ¨æ¬¢
    0.19
    -refresh
    0.18
    ˢ
    0.18
    æºĺ
    0.18
    whel
    0.18
    Activations Density 0.001%

    No Known Activations