© 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. 1556
    Prev
    Next
    INDEX
    Explanations

    logic or math

    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
    æľīæľŁå¾Ĵ
    -0.28
    è¿Ļ款车
    -0.27
     enthus
    -0.24
    ".↵↵↵↵
    -0.23
    âĩı
    -0.23
    /mit
    -0.22
    åħ¨æĺİæĺŁ
    -0.21
    criptor
    -0.21
    æĮ¦
    -0.20
     intimid
    -0.20
    POSITIVE LOGITS
    çݩ家æľĭåıĭ
    0.41
    é»ijæģ¶
    0.40
    æľīçļĦçݩ家
    0.32
    åħ¶å®ĥéĹ®é¢ĺ
    0.32
    游æĪı代
    0.30
    åºĶæĶ¶è´¦
    0.30
    éĽħé»ij
    0.29
    æĪķ
    0.29
    BOSE
    0.28
    æĸ°äººçݩ家
    0.28
    Activations Density 0.794%

    No Known Activations