© 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. 538
    Prev
    Next
    INDEX
    Explanations

    medical conditions

    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
    åħĭæĢĿ
    -0.38
    ä»İæł¹æľ¬
    -0.29
    æĢ§ä»·
    -0.25
    个çĻ¾åĪĨ
    -0.25
    åħ·æľīèī¯å¥½
    -0.23
     aDecoder
    -0.23
     még
    -0.22
     âĵĺ
    -0.22
    ãĢĤ",↵
    -0.22
    åIJĦè¡Į
    -0.22
    POSITIVE LOGITS
    lijah
    0.26
    icensing
    0.25
    以åıĬ
    0.24
    :expr
    0.24
    omanip
    0.23
    ancock
    0.23
    iami
    0.23
    brtc
    0.23
    ifestyles
    0.22
    alleries
    0.22
    Activations Density 6.893%

    No Known Activations