© 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. 6824
    Prev
    Next
    INDEX
    Explanations

    government officials and institutions

    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
    å¡ĺ
    -0.09
     Nec
    -0.09
    .Rotate
    -0.08
    lazy
    -0.08
    èĤ¤
    -0.08
    åıĺæĢģ
    -0.08
    åĩ½
    -0.08
    大éĩıçļĦ
    -0.08
    è´ª
    -0.08
    å°ĨåĨĽ
    -0.08
    POSITIVE LOGITS
    宥
    0.10
    asu
    0.09
    亲åĪĩ
    0.09
    æ¢ĵ
    0.09
    åıĹçģ¾
    0.09
    ç§ģèIJ¥
    0.09
    åIJ¬ä¼Ĺ
    0.09
    æħ°
    0.09
    æĹ¶è¡¨ç¤º
    0.09
    audi
    0.08
    Activations Density 0.131%

    No Known Activations