© 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. 344
    Prev
    Next
    INDEX
    Explanations

    Superlative

    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
     ConfigureServices
    -0.26
     PartialView
    -0.23
    upal
    -0.23
    scripción
    -0.22
    çĽijåIJ¬é¡µéĿ¢
    -0.22
    führung
    -0.20
    iseum
    -0.20
    åħ³éĶ®æĺ¯
    -0.20
    讹
    -0.19
    izophren
    -0.19
    POSITIVE LOGITS
     ever
    0.46
    -ever
    0.45
    ever
    0.44
    èİ«è¿ĩäºİ
    0.39
     possible
    0.37
     imaginable
    0.32
     EVER
    0.31
    ä¹ĭä¸Ģ
    0.31
    est
    0.30
    Ever
    0.30
    Activations Density 2.072%

    No Known Activations