© 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. 1827
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

    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
     beÄŁen
    -0.31
    SSIP
    -0.25
    ::.
    -0.22
    roken
    -0.22
     *)((
    -0.21
    ={"/
    -0.21
     **)&
    -0.21
    DrawerToggle
    -0.21
    ulerAngles
    -0.21
    irteen
    -0.20
    POSITIVE LOGITS
    ä¸Ģåı·
    0.28
    3
    0.24
    oriously
    0.23
    /vendors
    0.23
     III
    0.23
    äºĮ
    0.23
    :animated
    0.23
    1
    0.22
    2
    0.21
     Eins
    0.21
    Activations Density 3.151%

    No Known Activations