© 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. 6196
    Prev
    Next
    INDEX
    Explanations

    invention

    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
    éĽį
    -0.10
    纰
    -0.09
    ÑĮÑı
    -0.08
    нÑĤ
    -0.08
    åĬ³
    -0.08
    ä¸ĵæłı
    -0.08
    rid
    -0.08
    ubb
    -0.08
    主é¢ĺæ´»åĬ¨
    -0.08
    æ»ĩ
    -0.08
    POSITIVE LOGITS
    ÙħاÙħ
    0.09
    éĵ°
    0.09
    aras
    0.09
     seçenek
    0.08
    UNS
    0.08
    agment
    0.08
    ertainment
    0.08
    decorate
    0.08
    ment
    0.08
    èĢĥçłĶ
    0.08
    Activations Density 0.001%

    No Known Activations