© 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. 12118
    Prev
    Next
    INDEX
    Explanations

    profession titles followed by names

    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
    Not in Any Lists

    No Comments

    Negative Logits
    åĪ»æĦı
    -0.10
    å¾Ĵ
    -0.09
    ä¸Ģå¦ĤæĹ¢å¾Ģ
    -0.09
    åı£å¤´
    -0.09
    illegal
    -0.09
    ä¸īæľŁ
    -0.08
     Bound
    -0.08
    .UN
    -0.08
    æŃ»è§Ĵ
    -0.08
    æĹ©æľŁ
    -0.08
    POSITIVE LOGITS
    æŁIJ
    0.09
    viewer
    0.09
    boo
    0.08
    ündig
    0.08
    çĶŁçĹħ
    0.08
    rier
    0.08
     Lace
    0.08
    yles
    0.08
    _tick
    0.08
     Perspective
    0.08
    Activations Density 0.144%

    No Known Activations