© 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. 962
    Prev
    Next
    INDEX
    Explanations

    identification source

    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
    )){↵↵
    -0.24
     NONINFRINGEMENT
    -0.24
     indeb
    -0.23
    InParameter
    -0.23
    bbie
    -0.23
    .AppCompatActivity
    -0.23
    ómo
    -0.22
    enties
    -0.21
    .IsNullOrWhiteSpace
    -0.21
    xdf
    -0.21
    POSITIVE LOGITS
    æĹ¢
    0.22
    _RDWR
    0.22
    d
    0.20
    åĻª
    0.20
    åĮĢ
    0.20
     Gauss
    0.20
    çķĻè¨ĢæĿ¿
    0.19
     Unified
    0.19
    sat
    0.19
    eq
    0.18
    Activations Density 0.001%

    No Known Activations