© 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. 29645
    Prev
    Next
    INDEX
    Explanations

    Forum, application, markdown, IFO, wiki, .NET

    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
    èħ¾
    -0.09
    èij£
    -0.09
    pets
    -0.08
    pag
    -0.08
    æ»ļçIJĥ
    -0.08
    æł·åŃIJ
    -0.08
    /original
    -0.08
    èĶ·
    -0.08
     Kund
    -0.08
     PMC
    -0.08
    POSITIVE LOGITS
    æĹĦ
    0.10
    åľ¨æĪijåĽ½
    0.09
    åĮħåĽ´
    0.09
    åݿ级
    0.08
    ç¹ģ
    0.08
    çĶ¬
    0.08
    razier
    0.08
    illas
    0.08
    dit
    0.08
    avenport
    0.08
    Activations Density 0.042%

    No Known Activations