© 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. 1037
    Prev
    Next
    INDEX
    Explanations

    HTML tags and structure

    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
    }elseif
    -0.28
    à¸Ļà¹Ĥย
    -0.23
    âĺħâĺħ
    -0.23
    é³IJ
    -0.23
    xdc
    -0.21
    ",__
    -0.21
    éħŀ
    -0.21
    ðŁķij
    -0.21
    ($(".
    -0.20
    .MM
    -0.20
    POSITIVE LOGITS
    \Migrations
    0.20
    omanip
    0.20
    InlineData
    0.20
    acists
    0.20
    .'/'.$
    0.20
     else
    0.19
    serir
    0.19
    åįİå°Ķ
    0.19
    ifa
    0.19
    å«Ķ
    0.19
    Activations Density 0.796%

    No Known Activations