© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20820
    Prev
    Next
    INDEX
    Explanations

    party cadre

    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
    ä¸įå¾Ĺ转载
    -0.10
    们çļĦ
    -0.10
    é²Ķ
    -0.10
    åĬŀ好
    -0.10
    å®ĮäºĨ
    -0.09
    æĺ¯éĿŀ
    -0.09
    åľ¨ä¼łå¥ĩ
    -0.09
    ä½ĵåĨħ
    -0.09
    çIJĩ
    -0.09
    æĺ¯éŁ©åĽ½
    -0.09
    POSITIVE LOGITS
    人士
    0.10
    bound
    0.09
    -bound
    0.09
    9
    0.09
    antas
    0.08
    1
    0.08
     Tory
    0.08
    èĩ³æѤ
    0.08
    ovan
    0.08
    6
    0.08
    Activations Density 0.292%

    No Known Activations