© 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. 3506
    Prev
    Next
    INDEX
    Explanations

    theMethod used: Method 1Reason: MAX_ACTIVATING_TOKENS are all identical

    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
    /cards
    -0.21
    /terms
    -0.21
     borderTop
    -0.20
    ereo
    -0.20
    /interfaces
    -0.20
    kea
    -0.20
    .getOwnProperty
    -0.19
    渼
    -0.19
    meye
    -0.19
    äll
    -0.19
    POSITIVE LOGITS
    VERRIDE
    0.22
    ethylene
    0.21
    iferay
    0.19
    Segoe
    0.19
    µ
    0.18
    å°ıç¼ĸä¸Ģèµ·
    0.18
    ä¸įä¸ĭ
    0.18
    ë´ħ
    0.18
     sno
    0.18
    .loggedIn
    0.18
    Activations Density 0.062%

    No Known Activations