© 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. 49455
    Prev
    Next
    INDEX
    Explanations

    trump talent or override outnumber

    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
    åĩĨ
    -0.10
    æ¯Ķäºļ
    -0.09
    为åĩĨ
    -0.09
     вн
    -0.08
    ophe
    -0.08
    ä¸įå®ļ
    -0.08
    çĶµåı°
    -0.08
    olation
    -0.08
    bial
    -0.08
    aga
    -0.08
    POSITIVE LOGITS
    æѤåīį
    0.12
    ä¸ĢåĪĩ
    0.11
    ä»Ģä¹Īéĥ½
    0.11
    äºĨæĪijçļĦ
    0.10
    ä»»ä½ķå½¢å¼ı
    0.10
     any
    0.10
    æĸ°æīĭ
    0.10
    åħ¶ä½Ļ
    0.09
    éĤ£äºĽ
    0.09
    ä»»ä½ķ
    0.09
    Activations Density 0.034%

    No Known Activations