© 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. 2234
    Prev
    Next
    INDEX
    Explanations

    specific entities or 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
    engeance
    -0.23
     CircularProgress
    -0.21
    minent
    -0.20
     vej
    -0.20
    âİ£
    -0.19
     ($("#
    -0.19
     ="";↵
    -0.19
    aryawan
    -0.18
    çı©
    -0.18
    InMillis
    -0.18
    POSITIVE LOGITS
    isateur
    0.21
    ÐIJвÑĤо
    0.20
    .Val
    0.20
    .Tables
    0.20
    porto
    0.19
    tributes
    0.19
    }><
    0.19
    对ç«ĭ
    0.19
    .Ma
    0.19
    hoot
    0.18
    Activations Density 0.001%

    No Known Activations