© 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. 40377
    Prev
    Next
    INDEX
    Explanations

    personal anecdote or experience

    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
    æ¸ij
    -0.11
    æľīéĴ±
    -0.10
    æīĢèĥ½
    -0.10
    ä¹Łåıªèĥ½
    -0.10
    çļĦåħ´è¶£
    -0.09
    åİĿ
    -0.09
    çĹĪ
    -0.09
    å¾ĢåIJİ
    -0.09
    è¿Ļç¬Ķ
    -0.09
    è¿Ļ个åIJįåŃĹ
    -0.09
    POSITIVE LOGITS
    æľīä¸Ģ次
    0.12
    ä¸Ģä½į
    0.12
    åľ¨ä¸Ģ个
    0.12
    æŁIJ
    0.11
    æľīä¸Ģä½į
    0.11
    æĽ¾
    0.11
    æľī个
    0.10
    尤为
    0.10
    éķ¿è¾¾
    0.10
    æľīçļĦ
    0.10
    Activations Density 0.149%

    No Known Activations