© 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. 1051
    Prev
    Next
    INDEX
    Explanations

    sources or abbreviations

    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
     RequestMethod
    -0.20
    ROWSER
    -0.19
    ISC
    -0.19
     /*#__
    -0.19
    çĺ°
    -0.18
    ï¼ģ↵↵↵↵
    -0.18
    UILDER
    -0.18
    scrição
    -0.18
    æĶ¶æĶ¯
    -0.18
    æľĭåıĭ们对
    -0.18
    POSITIVE LOGITS
    plemented
    0.23
    ?('
    0.23
    />";↵
    0.22
    dzi
    0.22
    ligt
    0.21
    ulings
    0.21
    --)č↵
    0.21
    gles
    0.21
    assador
    0.20
    ounc
    0.20
    Activations Density 0.007%

    No Known Activations