© 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. 16545
    Prev
    Next
    INDEX
    Explanations

    long-lasting / lasting

    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
    outs
    -0.10
    çĿĢçľ¼
    -0.09
    è°ł
    -0.09
    å±Ĥåĩº
    -0.09
    uria
    -0.08
    çİ°åŃĺ
    -0.08
    èĮ´
    -0.08
    erna
    -0.08
    大èĩ£
    -0.08
     nonexistent
    -0.08
    POSITIVE LOGITS
    ly
    0.13
    ãģ¶ãĤĬ
    0.12
    ingly
    0.10
    gger
    0.10
    ently
    0.10
    ç³Ĭæ¶Ĥ
    0.10
    ä¸ĢèĤ¡
    0.09
    å·²ä¹ħ
    0.09
    ìłģìľ¼ë¡ľ
    0.09
    æĢ§çļĦ
    0.09
    Activations Density 0.024%

    No Known Activations