© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50095
    Prev
    Next
    INDEX
    Explanations

    aid organizations and workers

    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
    é²ģ
    -0.10
     triplet
    -0.09
    å¨ħ
    -0.09
    Õº
    -0.09
    èģĶç³»æĸ¹å¼ı
    -0.08
    åĬ¿
    -0.08
     finalized
    -0.08
    çļĦæ¯į亲
    -0.08
    æĺ¯æĪijåĽ½
    -0.08
     eg
    -0.08
    POSITIVE LOGITS
    èľ¡
    0.10
    é»Ŀ
    0.09
    ä»°
    0.09
     Than
    0.09
     shaded
    0.09
    amar
    0.08
     vat
    0.08
    rew
    0.08
    vat
    0.08
     ÙĪاÙĦع
    0.08
    Activations Density 0.086%

    No Known Activations