© 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. 2506
    Prev
    Next
    INDEX
    Explanations

    word beginnings

    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
    íĶĦë¡ľê·¸
    -0.28
    åĹIJ
    -0.24
    CLUDING
    -0.24
    âĦī
    -0.23
     Jad
    -0.23
     vÃŃde
    -0.22
    æģ¹
    -0.22
     (*((
    -0.21
     yarg
    -0.21
    âĺĿ
    -0.21
    POSITIVE LOGITS
    ä¼ĺ
    0.20
    hipster
    0.19
    0.19
     /*
    0.19
    顺
    0.19
     within
    0.19
     for
    0.19
     as
    0.18
    :↵↵
    0.18
     when
    0.18
    Activations Density 0.010%

    No Known Activations