© 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. 26277
    Prev
    Next
    INDEX
    Explanations

    wood construction or plant parts

    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
    åĿIJ
    -0.10
     Proto
    -0.08
    éĴİ
    -0.08
     Flip
    -0.08
    isi
    -0.08
    æľ´ç´ł
    -0.08
    flip
    -0.08
    ÑĤÑĭ
    -0.08
    é¼İ
    -0.08
    模ç³Ĭ
    -0.07
    POSITIVE LOGITS
     trunk
    0.12
    èĵĦ
    0.11
    åĺ»
    0.11
    æİĪä¿¡
    0.10
    åĽ´è§Ĥ
    0.10
    伤åı£
    0.10
    åı¯è¡ĮæĢ§
    0.10
    bens
    0.09
    åī¯ä¸»å¸Ń
    0.09
     Äiju
    0.09
    Activations Density 0.039%

    No Known Activations