© 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. 31694
    Prev
    Next
    INDEX
    Explanations

    existence or ceasing to exist

    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
     Memor
    -0.09
    åIJĽåŃIJ
    -0.09
    .serializer
    -0.09
    è¿ijä¹İ
    -0.09
    ç¼ĵ
    -0.09
    æ©Ħæ¦Ħ
    -0.09
    è¦ģä¸įè¦ģ
    -0.09
    æĪĺçķ¥æĢ§
    -0.09
    ä»Ħ
    -0.08
    åĩłä¹İ
    -0.08
    POSITIVE LOGITS
    ä»»ä½ķå½¢å¼ı
    0.10
    å®ŀä½ĵ
    0.10
    åĪ¶éĢł
    0.09
    çī©è´¨
    0.09
    æ£ļ
    0.09
     existence
    0.09
    çļĦåŃĺåľ¨
    0.09
    çī©ä½ĵ
    0.09
    çļĦæľ¬è´¨
    0.09
    äºĭçī©
    0.08
    Activations Density 0.188%

    No Known Activations