© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3340
    Prev
    Next
    INDEX
    Explanations

    9

    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
     semiclass
    -0.23
    .CreateIndex
    -0.23
    ç¥Ľæĸij
    -0.21
    alach
    -0.21
     pageNo
    -0.20
    ampire
    -0.20
    blockquote
    -0.19
    anske
    -0.19
    zcze
    -0.18
    olean
    -0.18
    POSITIVE LOGITS
     Türkiye
    0.24
    ">//
    0.23
    alsex
    0.23
     ".$_
    0.22
    :;↵
    0.21
    èݺ
    0.21
    âݤ
    0.21
    _visitor
    0.21
     (*((
    0.20
    0.20
    Activations Density 0.012%

    No Known Activations