© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50566
    Prev
    Next
    INDEX
    Explanations

    hydroponic irrigation in greenhouses

    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
    /tos
    -0.10
     Swe
    -0.10
    人人éĥ½
    -0.09
    åī¥
    -0.09
    éĶ»
    -0.09
    å¥ĸ
    -0.09
    çĪ
    -0.08
    toc
    -0.08
    èĤĿèĦı
    -0.08
     burnt
    -0.08
    POSITIVE LOGITS
    温室
    0.16
    大æ£ļ
    0.14
    çķ¦
    0.13
    çģĮæºī
    0.13
    æ£ļ
    0.12
    çķªèĮĦ
    0.11
    åŀĦ
    0.11
     greenhouse
    0.10
    hort
    0.10
     Hort
    0.10
    Activations Density 0.072%

    No Known Activations