© 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. 892
    Prev
    Next
    INDEX
    Explanations

    entry or start

    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
    ;o
    -0.31
     prive
    -0.31
    |;↵
    -0.30
    ,No
    -0.30
    |,↵
    -0.30
    .':
    -0.30
    ,Th
    -0.30
     suce
    -0.29
    );\↵
    -0.28
    ,},↵
    -0.28
    POSITIVE LOGITS
     masturbating
    0.33
    porno
    0.28
     ÑģенÑĤ
    0.28
     ÑģоÑĩеÑĤа
    0.26
    pmat
    0.26
    =".$_
    0.26
    licted
    0.26
    createClass
    0.25
    aylight
    0.24
    BASEPATH
    0.24
    Activations Density 12.042%

    No Known Activations