© 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. 12109
    Prev
    Next
    INDEX
    Explanations

    date stamps

    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
    åĩĢåĮĸ
    -0.09
    åĴĮæľįåĬ¡
    -0.09
    ç½ļ
    -0.09
    ëŀ©
    -0.09
    è¿Ļè¾ĪåŃIJ
    -0.09
    åľ¨ä»Ĭå¹´
    -0.09
    ç£Ķ
    -0.09
    æĹ©åľ¨
    -0.09
    assa
    -0.08
    ä¸Ģè¾ĪåŃIJ
    -0.08
    POSITIVE LOGITS
    æŁIJ
    0.09
    shm
    0.09
    çĸijä¼¼
    0.08
    bash
    0.08
    -long
    0.07
     Somebody
    0.07
    rab
    0.07
    æļ´
    0.07
    æĸĩä½ĵ
    0.07
    æĢį
    0.07
    Activations Density 0.141%

    No Known Activations