© 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. 54044
    Prev
    Next
    INDEX
    Explanations

    acts of helping others

    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
    室
    -0.09
    说åĪ°
    -0.08
    åľ¨çĶŁæ´»ä¸Ń
    -0.08
    æĢ»æĶ¶åħ¥
    -0.08
    åįĩ
    -0.08
    å¼ĵ
    -0.08
     inspir
    -0.08
    .syn
    -0.08
     Permanent
    -0.08
    dess
    -0.07
    POSITIVE LOGITS
    åħ¬çĽĬ
    0.16
    éĢłç¦ı
    0.15
    çĥŃå¿ĥ
    0.14
    åĬŁå¾·
    0.12
    è´¡çĮ®
    0.12
    帮å¿Ļ
    0.12
    æĭ¯æķij
    0.11
    åĸĦæĦı
    0.11
     обÑīеÑģÑĤв
    0.11
    帮åĬ©ä¼ģä¸ļ
    0.11
    Activations Density 0.067%

    No Known Activations