© 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. 47582
    Prev
    Next
    INDEX
    Explanations

    focal points, lens, ciliary

    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
    ufen
    -0.08
    bedo
    -0.08
     Drag
    -0.08
    åĥ»
    -0.08
    éºĴéºŁ
    -0.08
    éĻª
    -0.08
    ä¸Ĭåįĩ
    -0.08
     Branch
    -0.08
     drag
    -0.08
    /process
    -0.08
    POSITIVE LOGITS
     lenses
    0.12
    å±ł
    0.10
    è¿ijè§Ĩ
    0.10
    åįģ足
    0.09
    é»Ħæĺı
    0.09
    TRA
    0.09
    åĭī
    0.09
    çģµæ´»æĢ§
    0.09
    oola
    0.09
    pheric
    0.09
    Activations Density 0.097%

    No Known Activations