© 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. 1087
    Prev
    Next
    INDEX
    Explanations

    partial words

    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
    -0.37
    /**↵↵
    -0.28
     B
    -0.27
     V
    -0.27
     P
    -0.26
     W
    -0.26
    /filepath
    -0.26
     S
    -0.26
     _
    -0.26
     w
    -0.26
    POSITIVE LOGITS
     lucr
    0.50
     libertin
    0.48
     honda
    0.46
     testim
    0.46
     indeb
    0.45
     LENG
    0.44
     GANG
    0.44
    /Dk
    0.43
     resil
    0.43
     Prostit
    0.43
    Activations Density 15.508%

    No Known Activations