© 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. 60924
    Prev
    Next
    INDEX
    Explanations

    able to

    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
    çķĻä½ı
    -0.10
    è¶ĭ
    -0.09
    uba
    -0.08
    æİĽãģij
    -0.08
    ä»°
    -0.08
    æį·
    -0.08
    æIJŀ好
    -0.08
    å°ģ
    -0.08
    çķĻä¸ĭ
    -0.08
    æĭŁ
    -0.08
    POSITIVE LOGITS
    éĤ£æł·çļĦ
    0.09
    é«ĺ强度
    0.08
    pliers
    0.08
    å¾Ī容æĺĵ
    0.08
    强度
    0.08
    (grad
    0.08
    çĭIJçĭ¸
    0.08
    _EVENTS
    0.08
    ãĤ¢ãĥ¡ãĥª
    0.08
    å¤
    0.08
    Activations Density 1.551%

    No Known Activations