© 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. 57208
    Prev
    Next
    INDEX
    Explanations

    human-wildlife conflict

    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
    åºŁå¼ĥ
    -0.10
    OTS
    -0.09
    赶ä¸Ĭ
    -0.09
    奴éļ¶
    -0.09
    åŁºåĩĨ
    -0.09
    assel
    -0.09
    çĺ¦èº«
    -0.08
    æĬ¼
    -0.08
    ç¢İçīĩ
    -0.08
    ataka
    -0.08
    POSITIVE LOGITS
    éĺ¶æ®µæĢ§
    0.10
    管çIJĨèĢħ
    0.09
    åķĨä¸ļ模å¼ı
    0.09
    ç´¢èµĶ
    0.09
    éĹ¹
    0.09
     ÑħозÑıй
    0.09
    侵害
    0.09
    æ°ijçĶŁ
    0.09
    ç¥Ńç¥Ģ
    0.08
     Kun
    0.08
    Activations Density 0.050%

    No Known Activations