© 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. 24261
    Prev
    Next
    INDEX
    Explanations

    private and significant contexts

    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
    çĪĨåĩº
    -0.09
    rays
    -0.09
    å»ī
    -0.08
    å·®ä¸įå¤ļ
    -0.08
     Martins
    -0.08
    å¥
    -0.08
     GANG
    -0.08
    gan
    -0.08
    ساÙĨ
    -0.08
    èī¯æĢ§
    -0.08
    POSITIVE LOGITS
    亲å¯Ĩ
    0.12
    æļ§æĺ§
    0.11
    åľ¨åºĬä¸Ĭ
    0.10
     matters
    0.10
    ä»ĵä½į
    0.10
     personal
    0.10
    æ¦ľ
    0.09
    æķıæĦŁ
    0.09
     pes
    0.09
    ä»·ä½į
    0.09
    Activations Density 0.076%

    No Known Activations