© 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. 32335
    Prev
    Next
    INDEX
    Explanations

    website content, email updates

    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
    åıĮåIJij
    -0.11
    _RETRY
    -0.10
     ÑĦоÑĢ
    -0.09
     forg
    -0.09
    æĢ¥äºİ
    -0.08
    çļĦçĥŃæĥħ
    -0.08
    èĦı
    -0.08
    ogn
    -0.08
    UBL
    -0.08
    ä»Ĺ
    -0.08
    POSITIVE LOGITS
    ç»ĻæĤ¨
    0.09
    æı´
    0.09
    æı´åĬ©
    0.09
    帮åĬ©ä¼ģä¸ļ
    0.08
     lucr
    0.08
    æĪ¿åŃIJ
    0.08
    å¹²
    0.08
    Lux
    0.08
    帮å¿Ļ
    0.08
    éĵł
    0.08
    Activations Density 0.047%

    No Known Activations