© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59414
    Prev
    Next
    INDEX
    Explanations

    tone

    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
    Negative Logits
    们çļĦ
    -0.08
    åĬŀæ³ķ
    -0.08
    Ắ
    -0.08
    èĮµ
    -0.08
    uÃŃ
    -0.08
    æľįåĬ¡èĥ½åĬĽ
    -0.08
     dro
    -0.08
    è¸Ĭ
    -0.08
    å¼Ħ
    -0.08
     اÙĦØ¥Ùħ
    -0.08
    POSITIVE LOGITS
    åŁºè°ĥ
    0.10
    åIJĦå¼Ĥ
    0.10
    åĨ³å®ļäºĨ
    0.10
    缸åĬ©
    0.09
    æ·«
    0.09
    å·²ä¹ħçļĦ
    0.09
    ved
    0.09
    æ°Ķè´¨
    0.09
    弥漫
    0.09
    inator
    0.09
    Activations Density 0.009%

    No Known Activations