© 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. 3927
    Prev
    Next
    INDEX
    Explanations

    Acronyms and technical terms

    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
    -fw
    -0.22
    ocity
    -0.21
    ifu
    -0.21
    éĹ·
    -0.20
    ongs
    -0.20
    eri
    -0.19
    peats
    -0.19
    -pocket
    -0.19
    arence
    -0.18
     liner
    -0.18
    POSITIVE LOGITS
    æĭľå¸ĪåѦèīº
    0.22
     endwhile
    0.20
    :"-"`↵
    0.20
    ://${
    0.20
     Erectile
    0.19
     '((
    0.19
    çĬĦ
    0.19
    æĸ°æµªè´¢ç»ı
    0.19
    hausen
    0.19
    åıĪ好åıĪå¿«
    0.19
    Activations Density 0.002%

    No Known Activations