© 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. 976
    Prev
    Next
    INDEX
    Explanations

    sexual health products

    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
     molec
    -0.31
    traî
    -0.25
     neighb
    -0.24
    \
    -0.22
     setuptools
    -0.21
    ↵
    -0.21
    Ľ
    -0.20
    تغÙĬÙĬر
    -0.20
     dotenv
    -0.20
     berk
    -0.20
    POSITIVE LOGITS
     Erectile
    0.32
    ведÑĥÑī
    0.28
    ÑĤÑĢад
    0.27
    çݩ家æľĭåıĭ
    0.26
    (iOS
    0.25
    -UA
    0.24
     ksz
    0.24
    -League
    0.24
    struments
    0.24
    æľīçļĦçݩ家
    0.24
    Activations Density 0.254%

    No Known Activations