© 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. 48338
    Prev
    Next
    INDEX
    Explanations

    state for Palestinians

    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
    ç¥ł
    -0.09
    æ£ļ
    -0.09
    è¿Ļæī¹
    -0.09
    è´ŃæĪ¿
    -0.09
    好å¥ĩå¿ĥ
    -0.09
     sir
    -0.09
    æ¯ıä¸Ģ
    -0.08
    æ¸ħçIJĨ
    -0.08
    群ä½ĵ
    -0.08
     Meadows
    -0.08
    POSITIVE LOGITS
    æĪIJç«ĭ
    0.13
    æĶ¿æĿĥ
    0.11
    å¤Ń
    0.11
    è¦ģåģļ
    0.09
    å®ŀä½ĵ
    0.09
    æĪIJç«ĭäºĨ
    0.09
    æł·
    0.09
    è¿·ä½ł
    0.09
    æĹ·
    0.09
    è¯ŀçĶŁ
    0.09
    Activations Density 0.119%

    No Known Activations