© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 60572
    Prev
    Next
    INDEX
    Explanations

    ages in years

    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
    Negative Logits
    è¾ĩ
    -0.09
    管çIJĨåĴĮ
    -0.09
    ç®Ģ称
    -0.09
    æĢİä¹Ī说
    -0.09
    诰
    -0.09
    å¯Ĩ度
    -0.09
    åŁķ
    -0.08
    éĵ§
    -0.08
    åı²ä¸Ĭ
    -0.08
    èĽ±
    -0.08
    POSITIVE LOGITS
    amp
    0.10
    åħ¶å®ĥ
    0.09
    大纲
    0.09
    eters
    0.09
    åı¯èĥ½åıijçĶŁ
    0.08
    åħ¶æīĢ
    0.08
    åĪ«çļĦ
    0.08
    olia
    0.08
    èĩ³äºİ
    0.08
    /or
    0.08
    Activations Density 0.136%

    No Known Activations