© 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. 2579
    Prev
    Next
    INDEX
    Explanations

    numbers and percentages

    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
     notice
    -0.23
     spotted
    -0.22
    ItemAt
    -0.21
    écoute
    -0.21
     noticed
    -0.21
     Notice
    -0.20
    Notice
    -0.20
    notice
    -0.20
     rehe
    -0.20
     Spot
    -0.20
    POSITIVE LOGITS
    ï¼ģ');↵
    0.24
    å¿ŀ
    0.24
    ".↵↵↵↵
    0.22
    plusplus
    0.21
    %);↵
    0.21
    çĴģ
    0.21
    TED
    0.20
    .fromRGBO
    0.20
    åįģåŃĹ
    0.20
    æ·ı
    0.20
    Activations Density 0.053%

    No Known Activations