© 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. 3079
    Prev
    Next
    INDEX
    Explanations

    forces and enemies

    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
     hostages
    -0.31
     ';↵↵
    -0.23
     hostage
    -0.21
    indsight
    -0.20
    :o
    -0.20
    çīº
    -0.20
    )))));↵
    -0.20
    ëĵľë¦¬
    -0.20
    htmlspecialchars
    -0.20
    victim
    -0.20
    POSITIVE LOGITS
    æķĮ人
    0.28
    æĿ¥èĩª
    0.27
    对æīĭ
    0.27
     forces
    0.26
    æķĮ
    0.26
    ä¾Ĩèĩª
    0.25
    å¤ĸæĿ¥
    0.25
    æĿ¥è¢Ń
    0.25
     enemy
    0.25
    åĬ¿åĬĽ
    0.25
    Activations Density 0.621%

    No Known Activations