© 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. 1622
    Prev
    Next
    INDEX
    Explanations

    math and logic

    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
    çī¢è®°ä½¿åij½
    -0.27
    marginLeft
    -0.24
     alertController
    -0.23
     Fucking
    -0.23
     Thrones
    -0.22
    çļĦ带é¢Ĩ
    -0.22
     OTHERWISE
    -0.21
    marginTop
    -0.21
     ?>↵↵↵
    -0.21
    åĭł
    -0.21
    POSITIVE LOGITS
    /Dk
    0.28
    bove
    0.22
    -'.$
    0.22
    .RunWith
    0.21
    (Texture
    0.21
    thora
    0.21
    /Branch
    0.21
     (!((
    0.21
    .managed
    0.20
    uju
    0.20
    Activations Density 0.072%

    No Known Activations