© 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. 89
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    ystore
    -0.24
    ;amp
    -0.23
    isify
    -0.23
    ormsg
    -0.21
    ICTURE
    -0.20
    ihanna
    -0.20
    зван
    -0.20
    ยาย
    -0.19
     Decompiled
    -0.19
    acists
    -0.19
    POSITIVE LOGITS
    EDA
    0.21
    /TR
    0.20
    getManager
    0.20
    âĿĹ
    0.19
     */č↵č↵č↵
    0.19
    æľīçļĦçݩ家
    0.19
    å½Ŀ
    0.19
    éģ£
    0.19
    leton
    0.19
    -With
    0.19
    Activations Density 0.476%

    No Known Activations