© 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. 54068
    Prev
    Next
    INDEX
    Explanations

    sociology andsocial sciences

    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
    å¾µ
    -0.11
    å¾ģ
    -0.10
    壮大
    -0.10
    æī§æĶ¿
    -0.10
    æį©
    -0.09
    èĬ±å¼Ģ
    -0.09
    çĿ¹
    -0.09
    ÙĦاÙĨ
    -0.09
    å¾ģæ±Ĥ
    -0.08
     overse
    -0.08
    POSITIVE LOGITS
    çļĦ社ä¼ļ
    0.11
     Parsons
    0.09
    社æľĥ
    0.09
    夷
    0.09
    _SOC
    0.09
    社ä¼ļ
    0.09
    åĭ¾
    0.09
    æĸ°ä¸ī
    0.08
    ä»Ķ
    0.08
     ìĤ¬íļĮ
    0.08
    Activations Density 0.064%

    No Known Activations