© 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. 50696
    Prev
    Next
    INDEX
    Explanations

    us and people

    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
    å¤±æľĽ
    -0.10
    å¤ļåįĬ
    -0.10
    çĸı
    -0.10
    çĨŁ
    -0.09
    æĮĸ
    -0.09
    大ä¼Ĺ
    -0.09
    æľªèĥ½
    -0.09
     secular
    -0.08
     plain
    -0.08
    avar
    -0.08
    POSITIVE LOGITS
    å¥ĩèij©
    0.10
    åģİ
    0.09
    åıĪæĺ¯
    0.09
    çijķ
    0.09
    zu
    0.08
     ÑģÑĤали
    0.08
    oney
    0.08
     liability
    0.08
    çı¥
    0.08
    подоб
    0.08
    Activations Density 0.028%

    No Known Activations