© 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. 1257
    Prev
    Next
    INDEX
    Explanations

    code or programming

    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
     Erotic
    -0.38
     cunt
    -0.34
     enthus
    -0.32
     cuckold
    -0.31
     hentai
    -0.29
     erotica
    -0.28
    .Undef
    -0.27
     charisma
    -0.26
    WriteBarrier
    -0.25
     clit
    -0.25
    POSITIVE LOGITS
    ë°ı
    0.24
    .gb
    0.24
     entreprene
    0.23
    .setViewport
    0.23
     _
    0.22
    leground
    0.22
     numberWith
    0.21
     Mach
    0.21
     semantics
    0.21
    åĭł
    0.21
    Activations Density 2.940%

    No Known Activations