© 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. 3976
    Prev
    Next
    INDEX
    Explanations

    research studies

    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
    деÑģÑĮ
    -0.24
    andum
    -0.23
    доÑĢов
    -0.22
    å¹´ä¹ĭä¹ħ
    -0.21
     remix
    -0.21
    idente
    -0.19
     minHeight
    -0.19
     ÃĤu
    -0.18
    .UInt
    -0.18
    Ŀå§ĭ
    -0.18
    POSITIVE LOGITS
    ðŁĵIJ
    0.26
    hoot
    0.26
    âļĹ
    0.24
    âĮĤ
    0.23
    -FIRST
    0.21
    anmar
    0.20
    /↵↵↵↵
    0.20
    DrawerToggle
    0.20
    ðŁĺī
    0.20
    raith
    0.20
    Activations Density 0.001%

    No Known Activations