© 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. 63822
    Prev
    Next
    INDEX
    Explanations

    parades and processions

    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
    åºĬä¸Ĭ
    -0.09
    çĦ¦èĻij
    -0.09
    åĨ·éĿĻ
    -0.08
    æĢ¦
    -0.08
    é«ĺåİĭ
    -0.08
    å°Ĩèĩªå·±çļĦ
    -0.08
    åıijçĶŁäºĨ
    -0.08
    æīĵå·¥
    -0.08
    ibold
    -0.08
     poisoned
    -0.08
    POSITIVE LOGITS
    沿éĢĶ
    0.14
    沿线
    0.11
     parade
    0.11
    èµ°åĩº
    0.11
    å¯ĵæĦı
    0.11
     procession
    0.10
    æŃ¥è¡Į
    0.10
    å¾Ģå¹´
    0.10
    é¾Ļ
    0.10
    -route
    0.09
    Activations Density 0.074%

    No Known Activations