© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 30509
    Prev
    Next
    INDEX
    Explanations

    agriculture and farming

    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
    缼è¡Į
    -0.09
     Patterson
    -0.09
    è£ģ
    -0.09
    æĴ°
    -0.09
    èĻĵ
    -0.09
    ä¾ĽçĥŃ
    -0.08
    çĥŃæĴŃ
    -0.08
    -tm
    -0.08
    æµ·åºķ
    -0.08
    éĽªèĬ±
    -0.08
    POSITIVE LOGITS
    åĨľä¸ļ
    0.22
    åĨľæ°ij
    0.20
    gricult
    0.19
     agricultural
    0.18
    è¾²
    0.18
     farmer
    0.17
     agricult
    0.17
    åĨľä¸ļçĶŁäº§
    0.17
     agriculture
    0.17
    åĨľ
    0.17
    Activations Density 0.106%

    No Known Activations