© 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. 3138
    Prev
    Next
    INDEX
    Explanations

    C++ code

    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
    æįŁ
    -0.23
    <decltype
    -0.20
    getDb
    -0.20
    çī©ä¸ļ
    -0.19
     UnityEditor
    -0.19
    oux
    -0.19
    çŁ³
    -0.18
     tabBar
    -0.18
     Williams
    -0.18
    gypt
    -0.18
    POSITIVE LOGITS
    /Dk
    0.35
    amient
    0.28
     Xperia
    0.23
    izabeth
    0.22
    ðŁĵIJ
    0.22
    صÙĨد
    0.22
    VICE
    0.21
    IFn
    0.21
    åįĹæµ·ç½ij
    0.20
    @update
    0.20
    Activations Density 0.273%

    No Known Activations