© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2525
    Prev
    Next
    INDEX
    Explanations

    months and dates

    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
    jets
    -0.20
    -Compatible
    -0.19
    .usermodel
    -0.19
    ŀæĢ§
    -0.19
    pone
    -0.19
    对åħ¶çľŁå®ŀ
    -0.19
     UNU
    -0.19
     fullfile
    -0.19
    esse
    -0.18
    filer
    -0.18
    POSITIVE LOGITS
    çĸ¡
    0.22
    èĩ³ä»Ĭ
    0.21
    âı
    0.20
    .apiUrl
    0.19
    ago
    0.19
     Rubber
    0.19
    Äħd
    0.18
     term
    0.18
    }elseif
    0.18
    æĪªèĩ³çĽ®åīį
    0.18
    Activations Density 0.283%

    No Known Activations