© 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. 51978
    Prev
    Next
    INDEX
    Explanations

    growing conditions and harvest

    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
    å®ľå±ħ
    -0.09
    ç»Ħç»ĩå¼Ģå±ķ
    -0.09
    åģļä¸Ģ个
    -0.09
    atron
    -0.09
    ä¸Ģæĸ¹éĿ¢æĺ¯
    -0.09
    润æ»ijæ²¹
    -0.09
    kiye
    -0.08
    èį¯åĵģ
    -0.08
    çĴĥ
    -0.08
    åħļåı²
    -0.08
    POSITIVE LOGITS
    äº§åľ°
    0.12
    ä¾ĽåºĶåķĨ
    0.11
    ä¼ĺè¶Ĭ
    0.10
    ä¾Ľè´§
    0.10
     suppliers
    0.09
    AGE
    0.09
    Supplier
    0.09
     Supplier
    0.08
    çĶ£
    0.08
    åİŁæĿIJæĸĻ
    0.08
    Activations Density 0.260%

    No Known Activations