© 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. 1403
    Prev
    Next
    INDEX
    Explanations

    kind or sort

    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
    äºĨ好å¤ļ
    -0.32
    äºĨ好åĩł
    -0.29
    çĸ¥
    -0.23
    âĮĺ
    -0.23
    BOSE
    -0.22
    -divider
    -0.21
    سبÙĪع
    -0.20
    ︱
    -0.20
    çĽijåIJ¬é¡µéĿ¢
    -0.20
     useParams
    -0.20
    POSITIVE LOGITS
     kind
    0.38
    kind
    0.31
     sort
    0.30
    ç±»åŀĭçļĦ
    0.30
     kinds
    0.29
     démarche
    0.28
     latter
    0.26
    sort
    0.26
     sorts
    0.25
     same
    0.25
    Activations Density 1.542%

    No Known Activations