© 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. 7439
    Prev
    Next
    INDEX
    Explanations

    social 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
    pond
    -0.09
    æīĵåį¡
    -0.09
    åIJįå½ķ
    -0.09
    bolt
    -0.08
    æ¯ĶèµĽ
    -0.08
    åģ·
    -0.08
    ãģĮãģĤãģ£ãģ¦
    -0.08
    avad
    -0.08
    åīįè¡Į
    -0.08
    梵
    -0.08
    POSITIVE LOGITS
     sciences
    0.15
     Sciences
    0.11
    èĩªçĦ¶ç§ijåѦ
    0.10
     science
    0.10
    çĶŁçī©åѦ
    0.09
    ä¿Ł
    0.09
    çīĻ
    0.09
    çIJĨå·¥
    0.09
    é¢ĨåŁŁçļĦ
    0.09
    èĩªèIJ¥
    0.09
    Activations Density 0.060%

    No Known Activations