© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 4121
    Prev
    Next
    INDEX
    Explanations

    those

    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
    Negative Logits
    geries
    -0.26
    >Type
    -0.25
    对çħ§æ£ĢæŁ¥
    -0.24
    ãģĵãģ¨ãĤĤãģĤãĤĬãģ¾ãģĻ
    -0.23
    ÙĨÙĤص
    -0.22
     these
    -0.21
    /or
    -0.21
    .RelativeLayout
    -0.20
    nodeName
    -0.20
    istically
    -0.20
    POSITIVE LOGITS
    terdam
    0.25
    ÑĤвеÑĢжда
    0.24
    erable
    0.24
    [âĢ¦
    0.23
    ompiler
    0.23
    kke
    0.23
    esteem
    0.23
    ÑĤвеÑĢд
    0.23
    ettel
    0.23
     Erotic
    0.23
    Activations Density 0.075%

    No Known Activations