© 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. 1015
    Prev
    Next
    INDEX
    Explanations

    special characters

    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
    :NO
    -0.29
    ;o
    -0.27
    )./
    -0.26
    :black
    -0.26
    ;!
    -0.25
    ilmington
    -0.25
    raquo
    -0.25
    .JWT
    -0.25
    )","
    -0.25
    <=$
    -0.25
    POSITIVE LOGITS
     assistir
    0.22
    âħ
    0.21
     avaliações
    0.21
    udi
    0.21
     TCHAR
    0.20
    amen
    0.20
    présent
    0.19
    -T
    0.19
    ãĢħ
    0.19
    æ·ŀ
    0.18
    Activations Density 0.903%

    No Known Activations