© 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. 640
    Prev
    Next
    INDEX
    Explanations

    violence and death

    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
     sockfd
    -0.28
     Escorts
    -0.27
     readdir
    -0.22
     earthqu
    -0.22
     murderer
    -0.22
    arpa
    -0.21
     homic
    -0.21
     undercut
    -0.21
    æĥ¬æĦı
    -0.21
    ParticleSystem
    -0.20
    POSITIVE LOGITS
    äºĭ件
    0.33
    åıijçĶŁåľ¨
    0.32
    ðŁĵIJ
    0.28
     event
    0.28
    âļĹ
    0.27
     events
    0.26
     ë°ľìĥĿ
    0.25
     =>$
    0.25
    ï¼ģ');↵
    0.24
    âĮĤ
    0.23
    Activations Density 3.943%

    No Known Activations