© 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. 58240
    Prev
    Next
    INDEX
    Explanations

    kitchen appliances

    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
    APA
    -0.10
    ìĤ¬íķŃ
    -0.09
    ourt
    -0.09
    neo
    -0.09
    ãĤĪãģĨãģª
    -0.09
     Schmidt
    -0.09
    ote
    -0.09
    åķĨæĬ¥
    -0.08
     tá»ij
    -0.08
    OTE
    -0.08
    POSITIVE LOGITS
    tle
    0.10
    ä¸Ģ个éĹ®é¢ĺ
    0.09
    ving
    0.09
    ä¹İ
    0.09
    ey
    0.09
    fighter
    0.09
    屿
    0.09
    çķĮçļĦ
    0.09
    lined
    0.09
    æģª
    0.09
    Activations Density 0.005%

    No Known Activations