© 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. 513
    Prev
    Next
    INDEX
    Explanations

    gene citations

    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
     gratuits
    -0.24
     Å¡to
    -0.23
     Decompiled
    -0.23
    ãĢĤwww
    -0.20
    æºĺ
    -0.20
    Ĥæķ°
    -0.20
     Fla
    -0.20
    okable
    -0.19
    -0.19
    weathermap
    -0.19
    POSITIVE LOGITS
    :";č↵
    0.23
    .utf
    0.22
    :green
    0.21
    quist
    0.20
    .userInteractionEnabled
    0.20
    -League
    0.20
     :";↵
    0.19
    gend
    0.19
    irate
    0.19
    benh
    0.19
    Activations Density 0.187%

    No Known Activations