© 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. 930
    Prev
    Next
    INDEX
    Explanations

    programming operators

    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
    å®īå¿ĥ
    -0.20
    çŀĮ
    -0.19
    _CAST
    -0.19
    ä¹ĭæĺŁ
    -0.18
    ILLISECONDS
    -0.18
    endereco
    -0.18
    ÑĢеÑģÑĥÑĢÑģ
    -0.18
    ]-'
    -0.18
    inia
    -0.18
     Astro
    -0.17
    POSITIVE LOGITS
     !=
    0.34
     &&
    0.30
     ==
    0.30
    çļĦè¯Ŀ
    0.29
    æľīä»»ä½ķ
    0.26
    åħ¶ä»ĸçݩ家
    0.23
    çļĦ話
    0.22
    æĹĦ
    0.22
     !==
    0.21
    aternity
    0.21
    Activations Density 0.356%

    No Known Activations