© 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. 3650
    Prev
    Next
    INDEX
    Explanations

    copyright and license

    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
    ä¸Ģèĩ´å¥½è¯Ħ
    -0.32
    Ø£ÙĪض
    -0.24
    âĨµ
    -0.24
    ÙħÙĨØ°
    -0.23
    %!
    -0.22
     Mourinho
    -0.22
    è¿ĶåĽŀæIJľçĭIJ
    -0.22
    åĽ±
    -0.21
    åħļæĢ»
    -0.21
    åĴ»
    -0.21
    POSITIVE LOGITS
    DidAppear
    0.28
    rray
    0.26
    lrt
    0.25
    nika
    0.25
    clusão
    0.23
    dge
    0.22
    ngr
    0.22
    §è¡Į
    0.21
    uplic
    0.21
    entai
    0.21
    Activations Density 0.223%

    No Known Activations