© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1067
    Prev
    Next
    INDEX
    Explanations

    code structure

    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
    .apiUrl
    -0.26
    å®ŀäºĭæ±Ĥ
    -0.25
    :;↵
    -0.24
    ċ
    -0.22
    foundland
    -0.22
    wahl
    -0.21
    pery
    -0.20
    æ²Ĩ
    -0.20
    USART
    -0.20
    celain
    -0.19
    POSITIVE LOGITS
     QPointF
    0.22
    annonce
    0.21
    _Texture
    0.21
    entiful
    0.20
     Kun
    0.20
     пÑĢоÑģмоÑĤÑĢ
    0.20
     scale
    0.20
     figure
    0.19
     enthus
    0.19
    ↵↵
    0.19
    Activations Density 0.193%

    No Known Activations