© 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. 58905
    Prev
    Next
    INDEX
    Explanations

    incorporated, territory, delegate, continental

    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
    çĹķ
    -0.09
    é¾Ļ
    -0.08
    midd
    -0.08
    Chunks
    -0.08
    unds
    -0.08
    æľĹ
    -0.08
    eba
    -0.08
    潮湿
    -0.08
     disg
    -0.08
     recoil
    -0.08
    POSITIVE LOGITS
    讲
    0.09
    é«ĺéĢŁ
    0.09
    å¼ķ
    0.09
    æĭ©
    0.08
    å®ķ
    0.08
    建档
    0.08
    åĮ®
    0.08
    adian
    0.08
     Outlet
    0.08
    æŃ£å¸¸çļĦ
    0.08
    Activations Density 0.094%

    No Known Activations