© 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. 29573
    Prev
    Next
    INDEX
    Explanations

    aforementioned or mentioned

    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
    Negative Logits
    ç¿Ģ
    -0.08
    éķĽ
    -0.08
    spy
    -0.08
    æīª
    -0.08
    èĩªä»İ
    -0.08
    ç©·
    -0.08
    ston
    -0.08
    èĩº
    -0.08
    Ŀ
    -0.08
    nex
    -0.08
    POSITIVE LOGITS
    ä¸Ĭè¿°
    0.14
     aforementioned
    0.14
     afore
    0.10
    åīįè¿°
    0.10
    å¦ĤæѤ
    0.10
    åĪļæīį
    0.10
    éĤ£ä¹Ī
    0.09
     mentioned
    0.09
    mentioned
    0.09
    带æĿ¥çļĦ
    0.09
    Activations Density 0.580%

    No Known Activations