© 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. 1929
    Prev
    Next
    INDEX
    Explanations

    code and technical

    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
     preval
    -0.25
    çĶ·æľĭåıĭ
    -0.24
     jó
    -0.23
    ISTRIBUT
    -0.23
    itchens
    -0.23
    -awaited
    -0.22
    обилÑĮ
    -0.22
     antibiot
    -0.22
     jean
    -0.21
    ltre
    -0.21
    POSITIVE LOGITS
    itored
    0.26
    é²ij
    0.25
    xdb
    0.25
    BindView
    0.25
    еждÑĥ
    0.24
    .parseFloat
    0.23
    é³ķ
    0.23
    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    0.23
    olatile
    0.22
    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    0.22
    Activations Density 6.915%

    No Known Activations