© 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. 956
    Prev
    Next
    INDEX
    Explanations

    code or UI elements

    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
    è¸Ķ
    -0.20
     buc
    -0.20
    ButtonItem
    -0.20
    ндекÑģ
    -0.20
    _SF
    -0.20
    ð¬Ģ©
    -0.19
    .lineEdit
    -0.19
    stdint
    -0.19
    æĮ¹
    -0.18
    çĥĶ
    -0.18
    POSITIVE LOGITS
    '],$
    0.22
    slideDown
    0.20
    )init
    0.19
    olon
    0.19
    Become
    0.19
    urator
    0.18
    slideUp
    0.18
    íĢµ
    0.18
    )obj
    0.18
    .AutoSizeMode
    0.18
    Activations Density 0.438%

    No Known Activations