© 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. 26224
    Prev
    Next
    INDEX
    Explanations

    solve, find, or rescue

    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
    åĬ£
    -0.08
    å¾ħ
    -0.08
    awl
    -0.08
    ç¨ĭ度
    -0.08
     pic
    -0.07
    abb
    -0.07
    ä½łæĺ¯
    -0.07
    بدا
    -0.07
    aber
    -0.07
    缸å½ĵ
    -0.07
    POSITIVE LOGITS
    éĺ»æŃ¢
    0.10
    ä¿Ŀä½ı
    0.10
    ÑĪки
    0.10
    ç¢Ł
    0.10
    æīĴ
    0.10
    æĭ¯æķij
    0.10
    亲èĩª
    0.10
    线索
    0.09
    oron
    0.09
    çĪ±äºº
    0.09
    Activations Density 0.062%

    No Known Activations