© 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. 224
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    âĺ°
    -0.23
     MatSnackBar
    -0.20
    estruction
    -0.20
    Laughs
    -0.20
    Ú¤
    -0.20
    diÄŁi
    -0.19
    .qty
    -0.19
    olkien
    -0.19
    åĹ¥
    -0.19
     MatDialog
    -0.19
    POSITIVE LOGITS
     enthus
    0.28
    printStats
    0.25
    -strokes
    0.25
     necessitÃł
    0.25
    $LANG
    0.24
     íĨµíķ´ìĦľ
    0.23
    /slick
    0.23
     //~
    0.23
    OfDay
    0.22
    /respond
    0.21
    Activations Density 2.774%

    No Known Activations