© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 55238
    Prev
    Next
    INDEX
    Explanations

    resource efficiency and sustainability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    .exclude
    -0.09
    è¡Įä¸ļåıijå±ķ
    -0.08
    wav
    -0.08
    åĽŀæļĸ
    -0.08
    Interstitial
    -0.08
    agra
    -0.08
    åĪ¸åķĨ
    -0.08
     Advent
    -0.08
    SL
    -0.08
     Tent
    -0.08
    POSITIVE LOGITS
    èĭij
    0.09
    梵
    0.09
    饯
    0.09
    .resource
    0.08
    ç½Ħ
    0.08
    åħ±çĶŁ
    0.08
    鹿
    0.08
     bios
    0.08
    æīĢåľ¨çļĦ
    0.08
     resource
    0.08
    Activations Density 0.066%

    No Known Activations