© 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. 2767
    Prev
    Next
    INDEX
    Explanations

    comment markers

    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
    omat
    -0.23
    кÑĨион
    -0.23
    prar
    -0.23
    panse
    -0.23
    aira
    -0.22
    pson
    -0.22
    mite
    -0.22
    -chief
    -0.21
    geries
    -0.21
    itational
    -0.21
    POSITIVE LOGITS
    å¦Ĥæŀľæ²¡æľī
    0.25
    <Mesh
    0.23
     now
    0.22
    ä½Ĩçİ°åľ¨
    0.21
     Now
    0.21
     REGARD
    0.21
     ÐķÑģли
    0.20
    å¦Ĥæŀľæĺ¯
    0.20
     unless
    0.20
     Unless
    0.20
    Activations Density 0.022%

    No Known Activations