© 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. 27934
    Prev
    Next
    INDEX
    Explanations

    donating money for charity

    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
    æºľ
    -0.09
    çĤ¹å¤ļ
    -0.09
    åħ¥åı£
    -0.09
    ç¡ķ
    -0.09
    åįļå¼Ī
    -0.08
    ç¼ł
    -0.08
    麻å°Ĩ
    -0.08
    aru
    -0.08
    æ°Ķæģ¯
    -0.08
    akk
    -0.08
    POSITIVE LOGITS
    æħĪåĸĦ
    0.24
    åħ¬çĽĬ
    0.24
    æįIJ
    0.24
    æįIJèµł
    0.23
    æįIJçĮ®
    0.22
    åħ¬çĽĬæ´»åĬ¨
    0.22
     charity
    0.21
     donate
    0.20
     donation
    0.20
     charitable
    0.19
    Activations Density 0.169%

    No Known Activations