© 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. 27558
    Prev
    Next
    INDEX
    Explanations

    draws upon knowledge or experiences

    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
    anta
    -0.10
    å½ĵä¹ĭæĹłæĦ§
    -0.10
    åıĮèµ¢
    -0.10
    ante
    -0.10
    sst
    -0.09
    ANTA
    -0.09
    éĢIJæ¸IJ
    -0.09
    è·»
    -0.09
    åİ®
    -0.09
    å¼Ħ
    -0.08
    POSITIVE LOGITS
     expertise
    0.10
    代
    0.09
     ÐŀÐŀ
    0.09
    è¿ĩåİ»
    0.08
     experiences
    0.08
     lessons
    0.08
    ourd
    0.08
    ç»ıåħ¸
    0.08
    èŁ¾
    0.08
    à¸Ľà¸£à¸°à¸ªà¸ļ
    0.08
    Activations Density 0.013%

    No Known Activations