© 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. 3148
    Prev
    Next
    INDEX
    Explanations

    negligence

    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
     threat
    -0.24
     threatened
    -0.23
     Threat
    -0.23
    ÑĤиÑĢ
    -0.23
     threats
    -0.22
     createDate
    -0.22
    å¨ģèĥģ
    -0.22
    æħİéĩį
    -0.21
    threat
    -0.21
    ä¸Ģèĩ´å¥½è¯Ħ
    -0.21
    POSITIVE LOGITS
    责任
    0.31
     NEGLIGENCE
    0.28
    çļĦ责任
    0.28
     negligence
    0.25
    buat
    0.25
    ktop
    0.24
    çĸı
    0.24
    èµĶåģ¿
    0.24
     neglig
    0.23
     manslaughter
    0.23
    Activations Density 0.158%

    No Known Activations