© 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. 19616
    Prev
    Next
    INDEX
    Explanations

    Atlantic geography

    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
    ä¸Ńæŀ¢
    -0.09
    raction
    -0.09
    ç¼ĩ
    -0.09
    æįº
    -0.09
    енÑĮ
    -0.09
    heit
    -0.09
    ç¼Ģ
    -0.08
     Belmont
    -0.08
    éĺIJ
    -0.08
    çªĴ
    -0.08
    POSITIVE LOGITS
     Airways
    0.09
    ains
    0.09
    æĽ´å¤ļä¿¡æģ¯
    0.08
    Advisor
    0.08
    ä¸ĭéĿ¢å°±
    0.08
    ãģľ
    0.08
    ades
    0.08
    以ä¾Ĩ
    0.08
    广éĺĶ
    0.08
    ogh
    0.08
    Activations Density 0.009%

    No Known Activations