© 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. 2443
    Prev
    Next
    INDEX
    Explanations

    high

    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
    NullException
    -0.23
    elfast
    -0.22
     gode
    -0.22
    iferay
    -0.20
    TestId
    -0.20
    æĶ»åĩ»åĬĽ
    -0.20
    toDate
    -0.19
    >{!!
    -0.19
    bove
    -0.19
    creativecommons
    -0.19
    POSITIVE LOGITS
    .dtd
    0.29
    #af
    0.24
    ç¼ĩ
    0.24
     élè
    0.23
    VRT
    0.22
    èĭ¡
    0.21
    (er
    0.21
    DMA
    0.21
    #aa
    0.21
    "@
    0.20
    Activations Density 0.129%

    No Known Activations