© 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. 16702
    Prev
    Next
    INDEX
    Explanations

    news, announcements, or legal filings

    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
    ç®Ģ称
    -0.09
    ìĦ
    -0.09
     Ebony
    -0.08
    æĬĬè¿Ļ个
    -0.08
    èĻº
    -0.08
    ä¸Ńå°ı
    -0.08
    社ä¼ļä¿Ŀéļľ
    -0.07
    éĻįå¹ħ
    -0.07
    izu
    -0.07
    åı°è¯į
    -0.07
    POSITIVE LOGITS
    äºĮåŃĹ
    0.10
    åĽ°
    0.09
    ä»Ģä¹Īæł·
    0.09
    åĽĽä½į
    0.09
    ikk
    0.09
    _trap
    0.09
    .INSTANCE
    0.09
    landscape
    0.08
    æĪijå¿ĥéĩĮ
    0.08
    ç°ĭ
    0.08
    Activations Density 1.222%

    No Known Activations