© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-CHAT-65K
    7. 46933
    Prev
    Next
    INDEX
    Explanations

    ok and yes

    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/lmsys/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 192 tokens each
    Dataset (Dashboard)
    chanind/lmsys-chat-1m-qwen-2.5
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    建档ç«ĭ
    -0.23
    SMART
    -0.23
     registrazione
    -0.22
    TÃľ
    -0.21
    âĺħâĺħ
    -0.21
    PURE
    -0.21
    åħ³äºİæĪij们
    -0.21
    CNT
    -0.21
    åħļæĢ»
    -0.20
     Gün
    -0.19
    POSITIVE LOGITS
    ookies
    0.26
    ucch
    0.24
    [System
    0.23
    adiator
    0.23
    aeda
    0.23
    incinn
    0.22
    oload
    0.22
    regunta
    0.21
    /Peak
    0.20
    女æĢ§æľĭåıĭ
    0.20
    Activations Density 0.028%

    No Known Activations