© 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. 1486
    Prev
    Next
    INDEX
    Explanations

    biological pathways

    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
    综èīºèĬĤ缮
    -0.29
    riott
    -0.28
    çļĦ带é¢Ĩ
    -0.24
    ä»ħ代表
    -0.23
    Debe
    -0.22
    åĵ¢
    -0.22
    âĸ¿
    -0.21
    stery
    -0.21
     afterEach
    -0.21
    wpdb
    -0.20
    POSITIVE LOGITS
    >null
    0.25
    æľºåĪ¶
    0.24
    ç¼±
    0.23
    ,},↵
    0.21
    _ASSOC
    0.21
     Vaults
    0.21
    -Owned
    0.21
     ÑĤож
    0.21
     Blackhawks
    0.21
     effects
    0.21
    Activations Density 4.689%

    No Known Activations