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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21644
    Prev
    Next
    INDEX
    Explanations

    seeing or perspective

    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
    顺便
    -0.10
    çĩ¥
    -0.10
    åľ¨éĤ£éĩĮ
    -0.09
    大åĬĽæİ¨è¿Ľ
    -0.09
     chá»Ĺ
    -0.09
    è¯Ģ
    -0.08
    ç¥ŀä»Ļ
    -0.08
    çİĭçīĮ
    -0.08
     пеÑĢвой
    -0.08
    ç¿ħèĨĢ
    -0.08
    POSITIVE LOGITS
    çľĭå¾ħ
    0.15
    è§Ĩ为
    0.12
    è§Ĩ
    0.10
     differently
    0.10
     perspective
    0.10
    å½ĵä½ľ
    0.09
    æķ´ä¸ª
    0.09
    å½ĵåģļ
    0.09
     viewed
    0.09
     View
    0.09
    Activations Density 0.045%

    No Known Activations