© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8046
    Prev
    Next
    INDEX
    Explanations

    temperature and conditions

    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
    æ¯ģ
    -0.10
    æ¼ĵ
    -0.10
    å§Ķå±Ī
    -0.10
     resident
    -0.09
    oron
    -0.09
    åĢŁéĴ±
    -0.09
    æļ´éĽ¨
    -0.09
    ç͵影èĬĤ
    -0.08
    çļĦä¿¡ä»»
    -0.08
    æ³ķåζ
    -0.08
    POSITIVE LOGITS
    åĨ·
    0.12
    çĥŃéĩı
    0.12
    å¯Ĵ
    0.12
    温度
    0.11
    æļĸ
    0.11
    ä¿Ŀ温
    0.11
    çĥŃ
    0.10
    åĨ°åĨ·
    0.10
     warmth
    0.10
    ä½ĵ温
    0.10
    Activations Density 0.365%

    No Known Activations