© 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. 52857
    Prev
    Next
    INDEX
    Explanations

    sailing and boats

    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¦ģçŁ¥éģĵ
    -0.10
    åľ¨ä¸ĢæĹģ
    -0.10
    æİĪ
    -0.09
    è§Ħ模åĮĸ
    -0.09
    è¨Ģ
    -0.09
    ä¸Ģ侧
    -0.08
    æŃ£å¸¸ä½¿çĶ¨
    -0.08
     Nicar
    -0.08
    æĶ¹å»º
    -0.08
    بات
    -0.08
    POSITIVE LOGITS
    å¼Ģåı£
    0.11
    èĻ¹
    0.10
    å½¹
    0.09
    åı¯è§Ĩ
    0.09
    å®ī举
    0.09
    itten
    0.09
    åIJ®
    0.09
    _subplot
    0.08
    cores
    0.08
    弥漫
    0.08
    Activations Density 0.073%

    No Known Activations