© 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. 333
    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
    enor
    -0.18
     strdup
    -0.18
     Beste
    -0.18
    ayette
    -0.18
    permalink
    -0.18
     SECURITY
    -0.18
    åĭ¿
    -0.18
     maintenance
    -0.18
     både
    -0.18
    毡
    -0.17
    POSITIVE LOGITS
     RaycastHit
    0.27
    =localhost
    0.26
    ittings
    0.24
     activeClassName
    0.22
    ONGL
    0.22
     ÙĬÙĪس
    0.21
     تراÙħ
    0.21
    iếu
    0.20
    />.
    0.20
    иÑĩеÑģ
    0.20
    Activations Density 0.000%

    No Known Activations