© 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. 8712
    Prev
    Next
    INDEX
    Explanations

    JC Penney, Michael Cohen, tarot readers

    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
    ylie
    -0.09
    -properties
    -0.09
    ราà¸Ĭà¸ģาร
    -0.09
    ãģ¶ãĤĬ
    -0.08
    él
    -0.08
    æĺ¯ä¸įä¼ļ
    -0.08
    (exc
    -0.08
    rat
    -0.08
     çocuk
    -0.07
    comings
    -0.07
    POSITIVE LOGITS
    å¤ļå±Ĥ次
    0.10
    å±ij
    0.09
    å¼ıçļĦ
    0.09
    æİ¥åĬĽ
    0.09
    åıijè¾¾
    0.09
    åħ³éĶ®æŶåĪ»
    0.09
    vig
    0.08
    ä¸ĢåĪĨéĴŁ
    0.08
    éĽªå±±
    0.08
    æīĵå·¥
    0.08
    Activations Density 0.001%

    No Known Activations