© 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. 3175
    Prev
    Next
    INDEX
    Explanations

    to

    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
    åĹ¾
    -0.22
     coppia
    -0.21
     Kardash
    -0.21
    .sharedInstance
    -0.21
    jerne
    -0.21
    åĬ¼
    -0.20
    ç»ĦåĽ¾
    -0.20
     agréable
    -0.19
    åij¨åĪĬ
    -0.19
     nonatomic
    -0.19
    POSITIVE LOGITS
    PCS
    0.22
    anitize
    0.22
    uyến
    0.21
    UED
    0.21
    adero
    0.21
    oot
    0.20
    ðŁĶİ
    0.20
    agas
    0.20
    ='<?
    0.19
    ñe
    0.19
    Activations Density 0.149%

    No Known Activations