© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38690
    Prev
    Next
    INDEX
    Explanations

    living arrangements and residences

    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¸ĵä¸ļ人士
    -0.09
    å¸Ĥéķ¿
    -0.09
    便æ°ij
    -0.09
    è¡°
    -0.09
    pyx
    -0.09
     McGregor
    -0.09
     itemprop
    -0.09
    渺
    -0.09
    SEQU
    -0.08
    èĮ¸
    -0.08
    POSITIVE LOGITS
    室åıĭ
    0.14
    åħ¥ä½ı
    0.14
    å¯Ŀ
    0.14
    宿èĪį
    0.13
    å¯Ŀ室
    0.13
    ä½ı宿
    0.12
    楼å±Ĥ
    0.12
    女çĶŁ
    0.11
    åħ¬å¯ĵ
    0.10
    æ¨ĵ
    0.10
    Activations Density 0.165%

    No Known Activations