© 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. 3757
    Prev
    Next
    INDEX
    Explanations

    divine promises

    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
     mastur
    -0.23
    oric
    -0.22
     mend
    -0.22
    ipi
    -0.21
    uckland
    -0.21
     Zub
    -0.21
    pirit
    -0.20
    ç¦Ħ
    -0.19
     })();↵
    -0.19
     slee
    -0.18
    POSITIVE LOGITS
    :animated
    0.22
    .CG
    0.22
    @qq
    0.21
    ($(".
    0.21
    建档ç«ĭ
    0.21
    otence
    0.20
    ($('.
    0.19
     å®
    0.19
    ={"/
    0.19
    åĽĽä¸ªèĩªä¿¡
    0.19
    Activations Density 0.112%

    No Known Activations