© 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. 3743
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    addtogroup
    -0.25
    ä¸įæŃ»
    -0.22
    /*↵
    -0.21
    пÑģи
    -0.20
    quip
    -0.20
    åıĭæĥħéĵ¾æİ¥
    -0.20
    ocache
    -0.20
    åħ³äºİæĪij们
    -0.20
    ä¸Ģ大åłĨ
    -0.19
    eroon
    -0.19
    POSITIVE LOGITS
     AuÃŁerdem
    0.20
    noinspection
    0.19
    пÑĥÑģ
    0.19
    ãĤīãĤĮãģ¦ãģĦãģ¾ãģĻ
    0.18
     gele
    0.18
    dur
    0.18
    iful
    0.18
    ë³į
    0.18
     hely
    0.18
     Tween
    0.18
    Activations Density 0.000%

    No Known Activations