© 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. 2969
    Prev
    Next
    INDEX
    Explanations

    KIND

    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
    ame
    -0.20
    celand
    -0.20
     ><?
    -0.19
    uan
    -0.19
    indsight
    -0.19
     crit
    -0.19
     setPassword
    -0.18
    å½ĵãģ¦
    -0.18
     Lambert
    -0.18
    à¸ķà¸Ńà¸Ļ
    -0.18
    POSITIVE LOGITS
    ',//
    0.27
    MMdd
    0.27
    ,},↵
    0.25
    أخÙĪ
    0.24
    OUCH
    0.23
    uyá»ĥn
    0.23
    ')."
    0.22
    对åħ¶çľŁå®ŀ
    0.21
    ä¸ĭéĿ¢æĺ¯å°ı
    0.21
    UGIN
    0.21
    Activations Density 0.006%

    No Known Activations