© 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. 1256
    Prev
    Next
    INDEX
    Explanations

    mathematical code

    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
    izontal
    -0.20
    è°¤
    -0.20
     DirectoryInfo
    -0.19
    akedirs
    -0.19
    ;line
    -0.19
    ;"><?
    -0.19
    izont
    -0.19
    èĢĮåĩº
    -0.19
    [assembly
    -0.19
    digit
    -0.19
    POSITIVE LOGITS
     Ipsum
    0.24
    âĸ¿
    0.22
    RIPTION
    0.20
    /Dk
    0.20
    å§Ķç»Ħç»ĩ
    0.20
    .IsValid
    0.20
    楣
    0.20
     Stark
    0.19
    çªģåĩºéĹ®é¢ĺ
    0.19
    izia
    0.19
    Activations Density 0.386%

    No Known Activations