© 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. 26110
    Prev
    Next
    INDEX
    Explanations

    botanical classifications, morphology

    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
     coc
    -0.10
    æĬĺ磨
    -0.08
    agram
    -0.08
    使ä¹ĭ
    -0.08
    cka
    -0.08
    èĢĺ
    -0.08
    onda
    -0.08
    ä¸įèĩ³äºİ
    -0.08
     bev
    -0.08
    éķ¿æľŁ
    -0.08
    POSITIVE LOGITS
    åħ·ä½ĵæĥħåĨµ
    0.11
    åĺ´
    0.10
    åĪĨæł¡
    0.10
     hamm
    0.09
    èĩªæĿ¥
    0.09
    èµŀç¾İ
    0.09
    Comparator
    0.09
    frei
    0.09
    èĪįå¾Ĺ
    0.09
    åľ°åĿª
    0.09
    Activations Density 0.068%

    No Known Activations