© 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. 37148
    Prev
    Next
    INDEX
    Explanations

    years

    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¸ī天
    -0.12
     Days
    -0.12
    æķ´å¤©
    -0.11
    两天
    -0.11
    å½ĵ天
    -0.11
    æľĪæľ«
    -0.11
    è¿Ļåĩłå¤©
    -0.10
    ä¸Ģ天
    -0.10
    Days
    -0.10
    第äºĮ天
    -0.10
    POSITIVE LOGITS
    äºĶå¹´
    0.21
    åĩłå¹´
    0.20
    两年
    0.19
     years
    0.18
    ä¸īå¹´
    0.17
    åĽĽå¹´
    0.17
    åįģå¹´
    0.17
    äºĮåįģå¹´
    0.16
    å¹´éĻIJ
    0.16
    years
    0.15
    Activations Density 0.088%

    No Known Activations