© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 26
    Prev
    Next
    INDEX
    Explanations

    code and lists

    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
    __);
    -0.25
    requete
    -0.21
     Braun
    -0.21
     BALL
    -0.20
    ppelin
    -0.20
    æİĬ
    -0.20
    brace
    -0.19
    .FindAsync
    -0.19
    ronym
    -0.19
    bservable
    -0.19
    POSITIVE LOGITS
    usband
    0.22
     ============================================================================↵
    0.20
    ç«ĭãģ¦
    0.20
    ä»İæł¹æľ¬
    0.20
    åºŁ
    0.20
    å¾ĩ
    0.20
    ivos
    0.19
    .ImageAlign
    0.19
     jó
    0.19
    toISOString
    0.19
    Activations Density 0.001%

    No Known Activations