© 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. 647
    Prev
    Next
    INDEX
    Explanations

    narrative and abstract

    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
     overall
    -0.34
     unmist
    -0.34
     Overall
    -0.30
    Overall
    -0.29
    æĢ»ä½ĵ
    -0.26
     //================================================================
    -0.26
    overall
    -0.25
    ,unsigned
    -0.25
    åŁºäºİ
    -0.24
    å®ŀéĻħæĥħåĨµ
    -0.24
    POSITIVE LOGITS
     (~(
    0.30
    []{↵
    0.29
     }}>{
    0.29
    çľ¼è¢ĭ
    0.28
    åħļæĢ»
    0.28
    ALCHEMY
    0.28
    æĢ§ä»·
    0.26
    Ëĥ
    0.26
    /Internal
    0.26
    å´Ł
    0.25
    Activations Density 8.197%

    No Known Activations