© 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. 5646
    Prev
    Next
    INDEX
    Explanations

    Bangladesh

    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
     SLOT
    -0.10
    éĩįè¦ģåĨħ容
    -0.09
    çļ´
    -0.08
    lds
    -0.08
    _dispatch
    -0.08
    .mj
    -0.08
    éĤ£ä¸Ģ
    -0.08
    pac
    -0.08
    ix
    -0.08
     Ort
    -0.08
    POSITIVE LOGITS
    ood
    0.10
    es
    0.09
     Bik
    0.08
    éric
    0.08
    ëģĶ
    0.08
    æĭ¥æĮ¤
    0.08
    åIJĮä¸ļ
    0.08
    Boston
    0.08
    sing
    0.08
     Bangladesh
    0.08
    Activations Density 0.022%

    No Known Activations