© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19966
    Prev
    Next
    INDEX
    Explanations

    indigenous peoples and communities

    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
    æĺ¯éŁ©åĽ½
    -0.10
    ä¹ĭä½ľ
    -0.10
    åįİ人
    -0.10
    çĽ¸ä¼ł
    -0.10
    å¡ĺ
    -0.10
    åįİ侨
    -0.09
     Svens
    -0.09
    第äºĮæī¹
    -0.09
    æĥ³èµ·æĿ¥
    -0.09
    å·²ä¹ħ
    -0.09
    POSITIVE LOGITS
    åĵŃäºĨ
    0.10
    人士
    0.10
    æĭīæĸ¯
    0.08
    使å¾Ĺ
    0.08
    Instantiate
    0.08
    带走
    0.08
    cott
    0.08
    æľĭåıĭ
    0.08
    coma
    0.08
    lef
    0.08
    Activations Density 0.029%

    No Known Activations