© 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. 6146
    Prev
    Next
    INDEX
    Explanations

    increase, do, add

    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
    æ·³
    -0.10
    ç½ijéĢļ
    -0.10
    çĿ¡åīį
    -0.10
    åľ°åĿª
    -0.09
    åľ°ä¸Ń
    -0.09
    çļĦåģļæ³ķ
    -0.09
    绨
    -0.09
    çĻ¾äº¿
    -0.09
    ita
    -0.09
    äººæł¼
    -0.09
    POSITIVE LOGITS
    寻
    0.09
    oose
    0.09
    gon
    0.09
    åį±
    0.09
    кÑĢа
    0.08
    èµ·éĩį
    0.08
    osing
    0.08
    ood
    0.08
    OLF
    0.08
    侯
    0.08
    Activations Density 0.054%

    No Known Activations