© 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. 34154
    Prev
    Next
    INDEX
    Explanations

    cereal grain production

    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
    à¦ļ
    -0.09
    paces
    -0.09
    elf
    -0.09
     sheer
    -0.09
    ãģĵãģ¨ãĤĴ
    -0.09
    nable
    -0.09
    æĺ¯ä¸Ģéĥ¨
    -0.09
    ressed
    -0.08
    迤
    -0.08
    æĦł
    -0.08
    POSITIVE LOGITS
    lek
    0.10
    çĽĴåŃIJ
    0.09
    ç®ķ
    0.09
    rels
    0.09
    riages
    0.09
    abin
    0.09
    龸çİĭ
    0.08
    ties
    0.08
    itious
    0.08
    ä¹Łä¸º
    0.08
    Activations Density 0.016%

    No Known Activations