© 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. 1466
    Prev
    Next
    INDEX
    Explanations

    programming and data

    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
     showc
    -0.34
    UNET
    -0.31
     vÃŃde
    -0.30
     practition
    -0.30
     ksz
    -0.29
     Rencontre
    -0.27
     dumpsters
    -0.27
    ÃŃculo
    -0.26
     vegas
    -0.26
     lowes
    -0.26
    POSITIVE LOGITS
     scaleX
    0.32
     scaleY
    0.30
    Outlined
    0.27
     rapes
    0.27
     resembl
    0.27
    æĤ±
    0.26
    .setStroke
    0.25
    (strpos
    0.25
     Decompiled
    0.25
    iteDatabase
    0.25
    Activations Density 1.831%

    No Known Activations