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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51492
    Prev
    Next
    INDEX
    Explanations

    only

    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
    åĩ¡äºĭ
    -0.09
    yme
    -0.09
    inja
    -0.08
     велик
    -0.08
    çĶ³
    -0.08
    avis
    -0.08
    æĭĦ
    -0.08
    è·¯çģ¯
    -0.08
    æĦļ
    -0.08
    èĸĦå¼±
    -0.08
    POSITIVE LOGITS
    ä¸įå®ļ
    0.09
    æī¿æİ¥
    0.09
     hiá»ĩp
    0.09
    ìīIJ
    0.09
     Ramsey
    0.09
    âĺĢ
    0.08
    CAC
    0.08
    cÃŃ
    0.08
    Å¡ÃŃ
    0.08
    adow
    0.08
    Activations Density 0.012%

    No Known Activations