© 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. 24102
    Prev
    Next
    INDEX
    Explanations

    past and present states

    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
    åľ°ä½į
    -0.09
    æīĢæľī人éĥ½
    -0.09
    çļĦä¸Ģéĥ¨åĪĨ
    -0.09
    ä¸Ģçķª
    -0.09
    许å¤ļ人
    -0.09
    çļĦä¸Ģ项
    -0.09
    ä¸Ģè¶Ł
    -0.09
    对å¾ħ
    -0.09
    ä¸Ģ款
    -0.08
    æĺ¯ä¸Ģ项
    -0.08
    POSITIVE LOGITS
    /w
    0.09
    /c
    0.09
    /is
    0.09
    èĦ±èIJ½
    0.08
    eness
    0.08
    èIJĭ
    0.08
    _configure
    0.08
     denn
    0.08
    æİĩ
    0.08
    Teen
    0.08
    Activations Density 0.166%

    No Known Activations