© 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. 7041
    Prev
    Next
    INDEX
    Explanations

    plasma and waves eruption

    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
    è¡Įäºĭ
    -0.10
    ä¸įæŃ»
    -0.10
    æ®ĥ
    -0.09
    æµ®
    -0.09
     mob
    -0.09
    raz
    -0.09
    ä¸ĭä¾Ĩ
    -0.09
    çŀİ
    -0.09
    纯
    -0.08
    åĬŁ
    -0.08
    POSITIVE LOGITS
    æŁ¿
    0.10
    éĢĥ
    0.09
     Balt
    0.09
    çıĪ
    0.09
    社ä¼ļç»Ħç»ĩ
    0.09
    ảng
    0.09
    åī¯ä¸»ä»»
    0.08
    æ°ij主åħļ
    0.08
    è¯Ĭ
    0.08
    åħ¨çº¿
    0.08
    Activations Density 0.066%

    No Known Activations