© 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. 1381
    Prev
    Next
    INDEX
    Explanations

    code and programming

    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
     ámb
    -0.26
     miglior
    -0.24
     //!<
    -0.23
     sitios
    -0.23
    phants
    -0.22
     italiane
    -0.21
     letto
    -0.21
     incontri
    -0.21
     ><?
    -0.21
    andes
    -0.21
    POSITIVE LOGITS
    Ũ
    0.28
    Ĩ
    0.26
    .TXT
    0.26
    .yy
    0.26
    Ỹ
    0.26
    ],&
    0.25
    oftware
    0.25
    ðŁļ©
    0.25
    ?>>
    0.24
    readcr
    0.24
    Activations Density 2.065%

    No Known Activations