© 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. 12222
    Prev
    Next
    INDEX
    Explanations

    mill and threshing

    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
    çŃĩ
    -0.10
    #line
    -0.10
    imon
    -0.09
    loops
    -0.09
    å°ģ
    -0.09
    æķ°åŃĹ
    -0.08
    æĪİ
    -0.08
    ä¸į解
    -0.08
    alem
    -0.08
    èħ¾
    -0.08
    POSITIVE LOGITS
    æĻĴ
    0.10
     thresh
    0.10
    Äĥn
    0.09
    æīĵåĩ»
    0.09
    ä»ĭè´¨
    0.08
    æ·ĺæ±°
    0.08
    åIJ¹
    0.08
    çļĦåĬ¨åĬĽ
    0.08
     noop
    0.08
    侯
    0.08
    Activations Density 0.057%

    No Known Activations