© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1981
    Prev
    Next
    INDEX
    Explanations

    quantum

    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
     ÑģенÑĤ
    -0.35
    ç³ĸå°¿
    -0.34
    é£Łãģ¹ãģŁ
    -0.30
    é£Łãģ¹ãģ¦
    -0.29
     },{
    -0.29
    ('@/
    -0.28
    åħļå·¥å§Ķ
    -0.28
     fkk
    -0.28
    é£Łãģ¹ãĤĭ
    -0.27
    GPC
    -0.27
    POSITIVE LOGITS
     bureaucr
    0.49
     disadv
    0.43
     enthus
    0.33
    =@"
    0.32
     fierc
    0.32
    $__
    0.31
    NullOr
    0.29
     disastr
    0.29
    quisitions
    0.28
     schö
    0.28
    Activations Density 8.741%

    No Known Activations