© 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. 942
    Prev
    Next
    INDEX
    Explanations

    technical data fragments

    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
    :<?
    -0.73
    /Dk
    -0.71
    .za
    -0.67
    [".
    -0.64
    :'.$
    -0.64
    ',//
    -0.60
    :"-
    -0.58
    :NO
    -0.57
    }'",
    -0.57
    #ga
    -0.56
    POSITIVE LOGITS
     lingerie
    0.38
    _
    0.36
    2
    0.35
     pestic
    0.34
    1
    0.34
    3
    0.33
    0
    0.33
    ,
    0.33
    .
    0.32
    /
    0.32
    Activations Density 81.794%

    No Known Activations