© 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. 12207
    Prev
    Next
    INDEX
    Explanations

    unbiased or biased analysis/view

    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
    erset
    -0.10
    ected
    -0.09
     Dank
    -0.09
    è¿ĺ好
    -0.08
    urai
    -0.08
    elsen
    -0.08
    åĪ¶æĪIJ
    -0.08
    èµ·çłģ
    -0.08
    uyen
    -0.08
    æĺ¨æĹ¥
    -0.08
    POSITIVE LOGITS
    åĭº
    0.10
    è§ģè¯ģ
    0.10
    对å¾ħ
    0.09
    åħ¬æŃ£
    0.09
    ä¸ĭæĿ¥
    0.09
    æĹģ
    0.08
    ä¸Ģä¸ĭ
    0.08
     khá»ıi
    0.08
     ary
    0.08
    ç£
    0.08
    Activations Density 0.006%

    No Known Activations