© 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. 8433
    Prev
    Next
    INDEX
    Explanations

    humidity 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
    æĴŀ
    -0.09
    hawk
    -0.09
    upil
    -0.09
    æŁ¥çľĭ详æĥħ
    -0.08
    umpt
    -0.08
    lying
    -0.08
    å¯ĩ
    -0.08
    -too
    -0.08
     McGr
    -0.08
    è¿Ļ对
    -0.08
    POSITIVE LOGITS
    溽
    0.11
    çĻ¾å¼º
    0.10
    ities
    0.09
     Äijảo
    0.09
    çĹ¿
    0.09
    ÙĪØ¸
    0.09
    佬
    0.09
    ç·Ĭ
    0.09
    åĸĺ
    0.08
    ester
    0.08
    Activations Density 0.013%

    No Known Activations