© 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. 52268
    Prev
    Next
    INDEX
    Explanations

    last, first, period, years, months

    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
     Ñģобой
    -0.09
    楼
    -0.08
    å½ĵå±Ģ
    -0.08
    èĥĮåIJİçļĦ
    -0.08
    ลำ
    -0.08
    é¦ĸ
    -0.08
    éļıå¤Ħ
    -0.08
    å½ĵåľº
    -0.08
    lessly
    -0.08
    ï¸
    -0.08
    POSITIVE LOGITS
    ä¸įä¹ħ
    0.11
    å¹´éĹ´
    0.11
    è¿ĩç¨ĭä¸Ń
    0.10
    缮åīį为æŃ¢
    0.10
    otte
    0.10
     years
    0.09
     months
    0.09
    以æĿ¥
    0.09
    åĩłå¹´
    0.09
    åĩłä¸ªæľĪ
    0.09
    Activations Density 0.146%

    No Known Activations