© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3263
    Prev
    Next
    INDEX
    Explanations

    code terms

    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
    į°ìĿ´
    -0.24
    aramel
    -0.23
    achinery
    -0.21
    жÑĥ
    -0.21
     Mach
    -0.20
    æªĢ
    -0.19
    hum
    -0.19
    Calibri
    -0.19
     Hew
    -0.19
    istol
    -0.19
    POSITIVE LOGITS
    leetcode
    0.24
    .sendStatus
    0.20
    etCode
    0.20
    -widgets
    0.20
    uida
    0.19
    _sa
    0.19
    :type
    0.19
     Cooler
    0.19
    .IsSuccess
    0.19
     LV
    0.19
    Activations Density 0.026%

    No Known Activations