© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9063
    Prev
    Next
    INDEX
    Explanations

    inspirational figures

    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
    æİĮæı¡äºĨ
    -0.12
    èħ´
    -0.10
    åıĤä¸İ
    -0.10
    åıĤä¸İèĢħ
    -0.09
    ä¹ĭæĹħ
    -0.09
    夫
    -0.09
    çģµåĬ¨
    -0.09
     dÆ°
    -0.09
    éħįåģ¶
    -0.09
    æģĻ
    -0.09
    POSITIVE LOGITS
    æ¦ľæł·
    0.23
    æ¦ľ
    0.19
    楷
    0.16
    åģ¶åĥı
    0.15
    æłĩæĿĨ
    0.13
     inspirational
    0.13
     Inspir
    0.12
    模èĮĥ
    0.12
    Heroes
    0.11
    模仿
    0.11
    Activations Density 0.054%

    No Known Activations