© 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. 12097
    Prev
    Next
    INDEX
    Explanations

    projects, construction, and progress

    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
    æģ¢å¤įæŃ£å¸¸
    -0.11
    æ®ĭ
    -0.10
    å·¥ä½ľå®¤
    -0.10
    æ®ĺ
    -0.10
    PropertyParams
    -0.10
    ä¸ĩåĪĨ
    -0.10
    uco
    -0.09
     дек
    -0.09
    æĺ¯çľŁçļĦ
    -0.09
    欺
    -0.09
    POSITIVE LOGITS
    å¼Ģå·¥
    0.14
     projects
    0.13
    å¼Ģ工建设
    0.13
     Projects
    0.12
    é¡¹çĽ®çļĦ
    0.11
    é¡¹çĽ®å»ºè®¾
    0.11
    projects
    0.11
    åħ´å»º
    0.11
    é¡¹çĽ®
    0.11
    æł¸åĩĨ
    0.11
    Activations Density 0.113%

    No Known Activations