© 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. 3518
    Prev
    Next
    INDEX
    Explanations

    Additional

    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
     ÑĥÑĩиÑĤÑĭва
    -0.23
    STIT
    -0.23
    iare
    -0.23
    *>*
    -0.22
    .writeValue
    -0.21
     конÑģÑĤÑĢÑĥкÑĨи
    -0.21
    *>::
    -0.21
     equivalents
    -0.20
     redistribution
    -0.20
    YSTEM
    -0.20
    POSITIVE LOGITS
    /Private
    0.24
    .AI
    0.24
    ordinary
    0.23
    leftright
    0.21
    roupon
    0.21
    .Information
    0.21
    é¢Ŀå¤ĸ
    0.21
    поÑĩÑĤ
    0.21
    leine
    0.20
    éĤ³
    0.20
    Activations Density 0.058%

    No Known Activations