© 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. 5318
    Prev
    Next
    INDEX
    Explanations

    have or hold

    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
    hte
    -0.09
    çĶŁçĶŁ
    -0.08
    åģķ
    -0.08
    çļĦ羣å®ŀæĢ§
    -0.08
    çľ¼çľĭ
    -0.08
    è´¹çĶ¨
    -0.08
    æĬ¥ä¸ļ
    -0.08
    æİ¥åħ¥
    -0.08
    åħĨ
    -0.08
     Tel
    -0.08
    POSITIVE LOGITS
    æĮģæľīçļĦ
    0.14
    æīĭä¸Ń
    0.13
     holdings
    0.12
    æīĭä¸Ĭ
    0.12
    æĮģæľī
    0.12
     possession
    0.12
    æĶ¶èĹı
    0.11
    åºĵåŃĺ
    0.11
     ê°Ģì§Ģê³ł
    0.11
    å¤įåį°ä»¶
    0.11
    Activations Density 0.113%

    No Known Activations