© 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. 7170
    Prev
    Next
    INDEX
    Explanations

    european tour, philippines

    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
    å°¤åħ¶æĺ¯åľ¨
    -0.11
    å°¤åħ¶æĺ¯
    -0.10
    æ¯ķç«Ł
    -0.10
    ä¸Ģæĺ¯
    -0.09
     ведÑĮ
    -0.08
    ä½Ĩå®ĥ
    -0.08
    çī¹åĪ«æĺ¯åľ¨
    -0.08
    æīĢ以æĪij
    -0.08
     hem
    -0.08
    çļĦè®¤çŁ¥
    -0.08
    POSITIVE LOGITS
    åĢ¼å¾Ĺä¸ĢæıIJ
    0.12
    åı¦ä¸Ģè¾¹
    0.11
    说åĪ°
    0.11
    åĢ¼å¾Ĺ注æĦı
    0.11
    说å®Į
    0.10
    è°ĪåĪ°
    0.10
    æ¸Ĭ
    0.10
    伤
    0.10
    ãģĿãģ®ä»ĸ
    0.09
    å°ijä¸įäºĨ
    0.09
    Activations Density 0.050%

    No Known Activations