© 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. 1009
    Prev
    Next
    INDEX
    Explanations

    technical characters

    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
     desar
    -0.30
     perÃŃ
    -0.25
    getSingleton
    -0.24
     jihadist
    -0.24
    åĺ£
    -0.23
     acompaña
    -0.22
     //<
    -0.22
    isnan
    -0.21
    pleasant
    -0.20
    _EXEC
    -0.20
    POSITIVE LOGITS
    mát
    0.39
    -Compatible
    0.37
    /Dk
    0.35
    há»ķ
    0.35
    #ga
    0.34
    #aa
    0.34
    =-=-=-=-
    0.32
    @dynamic
    0.31
    'icon
    0.31
    .TXT
    0.31
    Activations Density 10.667%

    No Known Activations