© 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. 1001
    Prev
    Next
    INDEX
    Explanations

    et al

    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
    avanaugh
    -0.24
    assic
    -0.23
    磧
    -0.21
    迨
    -0.21
    ungeons
    -0.20
     ((*
    -0.20
    åİĨåı²æĸ°
    -0.20
    ingleton
    -0.20
    osate
    -0.19
     Playoff
    -0.19
    POSITIVE LOGITS
     et
    0.44
    çŃī人
    0.32
    è¿ĶåĽŀæIJľçĭIJ
    0.31
    ä»Ĭ天å°ıç¼ĸ
    0.30
    -scenes
    0.26
    çī¹åĪ«å£°æĺİ
    0.25
    .et
    0.25
    åı¯ä»¥æĽ´å¥½
    0.24
    ä¸ĭéĿ¢å°ıç¼ĸ
    0.23
    ï¹¢
    0.23
    Activations Density 0.486%

    No Known Activations