© 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. 3408
    Prev
    Next
    INDEX
    Explanations

    legal warranties

    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
    leanor
    -0.21
    å°±å¤Ł
    -0.21
    ç°ł
    -0.19
    æªł
    -0.19
    heed
    -0.19
    çªģ
    -0.19
    /animate
    -0.19
    EVER
    -0.18
     маÑģло
    -0.18
     UNICODE
    -0.18
    POSITIVE LOGITS
     practition
    0.23
    ennifer
    0.21
    oÄŁlu
    0.20
    é¹ŀ
    0.20
    .Interop
    0.20
     manh
    0.19
    doi
    0.19
    Jeste
    0.19
    quete
    0.18
    abyrinth
    0.18
    Activations Density 0.002%

    No Known Activations