© 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. 1755
    Prev
    Next
    INDEX
    Explanations

    CSS selectors

    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
     AppModule
    -0.22
    äºĮæľŁ
    -0.21
    æIJŀ
    -0.20
     typingsJapgolly
    -0.20
    érique
    -0.20
    满èĦ¸
    -0.20
    /mit
    -0.19
    æµĵæµĵ
    -0.19
     beforeSend
    -0.19
     obsolete
    -0.18
    POSITIVE LOGITS
    :CGRect
    0.25
     UClass
    0.24
    odie
    0.23
    游æĪıæĬĢå·§
    0.23
    åĨħçļĦ
    0.23
     *,↵
    0.22
    CEE
    0.21
    iblings
    0.21
    gota
    0.20
    ðŁĻĤ
    0.20
    Activations Density 0.265%

    No Known Activations