© 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. 3900
    Prev
    Next
    INDEX
    Explanations

    technical text 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
     typings
    -0.20
    åĬ¿
    -0.20
    ati
    -0.20
     gan
    -0.19
    asury
    -0.19
    éĥ¨åī¯
    -0.19
     ancest
    -0.19
     typingsJapgolly
    -0.19
     glimps
    -0.19
    .newLine
    -0.19
    POSITIVE LOGITS
    )(__
    0.26
    ANGLES
    0.24
    izona
    0.23
     REUTERS
    0.23
    Ñŀ
    0.23
    DCF
    0.22
    .rar
    0.22
    )||(
    0.21
    -Shirt
    0.21
     malaysia
    0.21
    Activations Density 0.001%

    No Known Activations