© 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. 2361
    Prev
    Next
    INDEX
    Explanations

    news topics

    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
     ['./
    -0.24
    èĻĵ
    -0.22
    ãİĿ
    -0.22
    -0.21
     scaleY
    -0.21
     ALOG
    -0.21
    ActivityIndicator
    -0.21
    æ·ı
    -0.21
     XCT
    -0.21
    setattr
    -0.21
    POSITIVE LOGITS
    ();++
    0.24
    ffield
    0.23
    udeau
    0.23
    (*)(
    0.22
    oriously
    0.22
     "-//
    0.22
    ç»Ĩç»Ĩ
    0.22
    ytut
    0.21
    éĻªä½ł
    0.21
    redient
    0.21
    Activations Density 2.200%

    No Known Activations