© 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. 906
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
     licensors
    -0.25
    /vendors
    -0.23
    绺
    -0.20
    âĦī
    -0.19
    .BorderFactory
    -0.19
    AsyncResult
    -0.19
    踯
    -0.19
    æľ¬ç½ij
    -0.19
    津贴
    -0.18
    ([]*
    -0.18
    POSITIVE LOGITS
     DataGridViewCellStyle
    0.23
    [sizeof
    0.23
    ropri
    0.22
    ì¤į
    0.21
    criptors
    0.20
    èļ¤
    0.20
     Coat
    0.19
    æİĸ
    0.19
    NamedQuery
    0.19
     >",
    0.19
    Activations Density 0.010%

    No Known Activations