© 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. 2689
    Prev
    Next
    INDEX
    Explanations

    titles and phrases

    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
    -mf
    -0.28
     ><?
    -0.28
    *)((
    -0.25
    "class
    -0.24
    AFX
    -0.23
    imulator
    -0.23
    æŁ¥çľĭ详æĥħ
    -0.22
     defaultProps
    -0.21
    ":-
    -0.20
    );$
    -0.20
    POSITIVE LOGITS
    ocus
    0.20
     Shooter
    0.19
    ÑĭÑĪ
    0.19
    rück
    0.19
    olle
    0.18
    بة
    0.18
     Contractor
    0.18
    ScreenState
    0.18
    bundles
    0.17
    åij¼
    0.17
    Activations Density 0.009%

    No Known Activations