© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52812
    Prev
    Next
    INDEX
    Explanations

    successful period

    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
    åĩºæ±Ĺ
    -0.11
    庵
    -0.10
    æĺ¯ä¸Ģä½į
    -0.09
    éļ¨æĻĤ
    -0.09
    å§ĭç»ĪåĿļæĮģ
    -0.09
    NCY
    -0.09
    设æĸ½
    -0.09
    ä¼İ
    -0.09
    éļıæŶ
    -0.09
    æ¶Īè´¹åĵģ
    -0.09
    POSITIVE LOGITS
    çļĦæĹ¥åŃIJ
    0.11
    æĹ¥åŃIJ
    0.11
    ä¸Ģ段
    0.10
    ä¸į失
    0.10
    æĹ¶æľŁ
    0.10
    çļĦæĹ¥åŃIJéĩĮ
    0.10
     years
    0.09
     days
    0.09
    ä¸Ģ页
    0.09
     денÑĮ
    0.09
    Activations Density 0.119%

    No Known Activations