© 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. 36181
    Prev
    Next
    INDEX
    Explanations

    study designed to compare

    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
    ä»ĺ
    -0.08
    缸
    -0.08
    è¹Ħ
    -0.08
    æ§
    -0.08
    ä¿Ŀæ´ģ
    -0.08
    æĬĬèĩªå·±çļĦ
    -0.08
    âĺİ
    -0.08
     ÐŀÑģобенно
    -0.08
    çĥĪ
    -0.08
    éĤ£æĺ¯
    -0.08
    POSITIVE LOGITS
    åĭŁéĽĨ
    0.11
    æĵ
    0.09
    æı¿
    0.09
    æĭĽåĭŁ
    0.09
    çŁ¥æĥħ
    0.09
    åħ¶å®ĥéĹ®é¢ĺ
    0.08
    âĨĹ
    0.08
    åIJĪéĢĤçļĦ
    0.08
    çĶ¨èį¯
    0.08
    人æ°Ķ
    0.08
    Activations Density 0.143%

    No Known Activations