© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2334
    Prev
    Next
    INDEX
    Explanations

    vacation travel

    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
    TransparentColor
    -0.24
    :".$
    -0.23
    æµ®
    -0.21
    溯
    -0.21
    .showMessageDialog
    -0.21
    -relative
    -0.21
    -uppercase
    -0.20
    xit
    -0.20
    nych
    -0.20
    /Library
    -0.20
    POSITIVE LOGITS
    æĦ«
    0.23
    ormsg
    0.22
     erotica
    0.20
     Tourism
    0.18
     OTA
    0.18
     Fälle
    0.18
    åĨįåİ»
    0.18
    wizard
    0.18
    æĭ¿åĩºæĿ¥
    0.18
    èı½
    0.18
    Activations Density 0.210%

    No Known Activations