© 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. 3892
    Prev
    Next
    INDEX
    Explanations

    programming and data

    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
    éĺµéĺµ
    -0.23
    ç»ij
    -0.19
     bound
    -0.19
    =?";↵
    -0.19
    .InnerException
    -0.18
    éĺ³
    -0.18
    æĺ¯ä¸įæĺ¯
    -0.18
    :UITableView
    -0.18
    (strategy
    -0.18
    (&(
    -0.17
    POSITIVE LOGITS
     Girlfriend
    0.24
    rame
    0.23
    elts
    0.23
    orman
    0.23
     recru
    0.22
    berra
    0.21
    illisecond
    0.21
     buc
    0.21
    anuts
    0.20
    /effects
    0.20
    Activations Density 0.001%

    No Known Activations