© 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. 3906
    Prev
    Next
    INDEX
    Explanations

    technical import

    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
     ElseIf
    -0.23
    ddit
    -0.23
    phem
    -0.22
     slik
    -0.22
    ï¸ı
    -0.20
    ksam
    -0.19
    issions
    -0.19
    ÙĬØ«
    -0.19
    }_${
    -0.19
    çijļ
    -0.18
    POSITIVE LOGITS
    ¡°
    0.27
     busty
    0.21
    éĽ¹
    0.20
    çĴĢ
    0.20
    Č↵
    0.20
     Swe
    0.19
    %"><
    0.19
    ']=="
    0.19
     CascadeType
    0.19
    便
    0.19
    Activations Density 0.005%

    No Known Activations