© 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. 1229
    Prev
    Next
    INDEX
    Explanations

    academic fields

    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
     snapchat
    -0.26
    åĹ«
    -0.25
    'options
    -0.25
     ergonomic
    -0.24
     ketogenic
    -0.23
     winger
    -0.23
     midfielder
    -0.23
    ummings
    -0.23
     matchup
    -0.22
     preseason
    -0.21
    POSITIVE LOGITS
    .lu
    0.30
    çļĦ带é¢Ĩ
    0.28
    comings
    0.25
    -prepend
    0.25
     physical
    0.25
     human
    0.24
    èµĸ以çĶŁåŃĺ
    0.23
    !important
    0.23
    .AutoComplete
    0.23
    ¾ç¤º
    0.23
    Activations Density 8.943%

    No Known Activations