© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 741
    Prev
    Next
    INDEX
    Explanations

    spatial offsets and scale

    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
    []{↵
    -0.26
    çݩ家æľĭåıĭ
    -0.26
    >Status
    -0.23
    xing
    -0.23
    .Ticks
    -0.22
     "(\<
    -0.22
     fkk
    -0.21
    .predicate
    -0.21
    Êī
    -0.21
    swers
    -0.21
    POSITIVE LOGITS
     scaleX
    0.34
     scaleY
    0.29
     translateY
    0.26
     novitÃł
    0.24
     ArgumentNullException
    0.22
     offsetY
    0.22
     yOffset
    0.21
    .FileReader
    0.21
     ])->
    0.21
    thumbnails
    0.20
    Activations Density 0.367%

    No Known Activations