© 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. 17679
    Prev
    Next
    INDEX
    Explanations

    charitable organizations and philanthropy

    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
    便æĺ¯
    -0.10
    å½ķ
    -0.09
    ä¹ĹãĤĬ
    -0.09
    御
    -0.08
    rips
    -0.08
    é²ľæĺİ
    -0.08
     Laur
    -0.08
    ä¸İåIJ¦
    -0.08
    便
    -0.08
    é¢Ĺ
    -0.08
    POSITIVE LOGITS
    æħĪåĸĦ
    0.18
    社ä¼ļç»Ħç»ĩ
    0.14
    åħ¬çĽĬ
    0.14
     charitable
    0.13
     charity
    0.12
    æ°ijæĶ¿
    0.12
    åŁºéĩijä¼ļ
    0.11
     philanth
    0.11
    æħĪæĤ²
    0.10
    æ°ijæĶ¿å±Ģ
    0.10
    Activations Density 0.114%

    No Known Activations