© 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. 3505
    Prev
    Next
    INDEX
    Explanations

    code and numbers

    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
    NgModule
    -0.25
    unner
    -0.25
    okie
    -0.23
    nü
    -0.22
    okable
    -0.22
    rlen
    -0.21
    urple
    -0.21
    AuthGuard
    -0.21
     StraÃŁen
    -0.20
    )=='
    -0.20
    POSITIVE LOGITS
    åıĭæĥħéĵ¾æİ¥
    0.23
    s
    0.21
    ä¾®
    0.21
    建档ç«ĭ
    0.21
    çİŁ
    0.20
    es
    0.19
    åħ³äºİæĪij们
    0.19
    .setItems
    0.19
    åĶ¬
    0.19
    ç½ijé¦ĸ页
    0.18
    Activations Density 0.019%

    No Known Activations