© 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. 788
    Prev
    Next
    INDEX
    Explanations

    legal and business

    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
    :numel
    -0.28
    .vertx
    -0.26
    AndView
    -0.24
    |#
    -0.23
    ;line
    -0.23
    elters
    -0.22
    atat
    -0.21
    tener
    -0.21
    ":[{↵
    -0.21
    :length
    -0.21
    POSITIVE LOGITS
    /is
    0.37
     Ñģобой
    0.35
     itself
    0.30
    irlines
    0.28
    (ed
    0.27
    ä½Ĩä¸įéĻIJ
    0.27
    ãİľ
    0.26
    å¼Ģå¥ĸç»ĵæŀľ
    0.25
     us
    0.25
    ä¸Ģèĩ´å¥½è¯Ħ
    0.24
    Activations Density 4.410%

    No Known Activations