© 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. 1753
    Prev
    Next
    INDEX
    Explanations

    numbers and statistics

    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°±ç»Ļ大家
    -0.24
    çļĦåIJĪä½ľ
    -0.21
    âĦ¹
    -0.21
    æĭľå¸ĪåѦèīº
    -0.20
    åŃ£åIJİ
    -0.20
    å°ıç¼ĸä¸Ģèµ·
    -0.20
    amble
    -0.20
    Club
    -0.19
    ðŁļ©
    -0.19
     actionTypes
    -0.19
    POSITIVE LOGITS
    orgeous
    0.30
    ë°¤
    0.25
    }elseif
    0.22
    è¨ĩ
    0.21
    æľĭåıĭ们对
    0.21
     männ
    0.20
    åľ¨åĵª
    0.20
    ê³łìļĶ
    0.20
     thá»ķ
    0.20
    çĤĿ
    0.20
    Activations Density 0.969%

    No Known Activations