© 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. 1697
    Prev
    Next
    INDEX
    Explanations

    code terms

    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
     ($("#
    -0.23
    .AppendFormat
    -0.22
     ($('#
    -0.22
    alborg
    -0.22
     !=↵
    -0.21
    èµ°åĩºæĿ¥
    -0.21
    DUCT
    -0.21
    VersionUID
    -0.20
     Rencontres
    -0.20
    -initialized
    -0.20
    POSITIVE LOGITS
    ascript
    0.21
    ä¸įåħĭ
    0.20
    广æĴŃ
    0.20
    åı¯æĥ³
    0.20
    intree
    0.20
    weathermap
    0.20
    adin
    0.20
    ().'/
    0.20
    HWND
    0.19
    oproject
    0.19
    Activations Density 0.737%

    No Known Activations