© 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. 57669
    Prev
    Next
    INDEX
    Explanations

    yeast cerevisiae saccharomyces

    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
     Burl
    -0.09
    è¿İ
    -0.09
    çį¾
    -0.08
     Hayden
    -0.08
    .experimental
    -0.08
     HEAP
    -0.08
    为é¦ĸ
    -0.08
    空
    -0.08
    æݼ
    -0.08
    åŀ«
    -0.08
    POSITIVE LOGITS
    éĨª
    0.11
    æļ¹
    0.10
    群
    0.10
    ÑĢаж
    0.09
    éŃĦ
    0.09
    éħµ
    0.09
    åħļæĢ»
    0.09
    æĿ¯
    0.09
     amateurs
    0.09
    æľĶ
    0.09
    Activations Density 0.128%

    No Known Activations