© 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. 40242
    Prev
    Next
    INDEX
    Explanations

    lone, stray, rogue

    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
    讼
    -0.09
    å°Ķæĸ¯
    -0.09
    inus
    -0.09
    æѤæ¡Ī
    -0.09
     Äijỡ
    -0.09
    ä¼ijæģ¯
    -0.09
    ×ķף
    -0.08
    SURE
    -0.08
    arian
    -0.08
    ä¸įä¸ĭ
    -0.08
    POSITIVE LOGITS
    0.09
    ancies
    0.09
     fancy
    0.09
    éric
    0.09
    chk
    0.08
    åºľ
    0.08
    ullet
    0.08
    té
    0.08
    ork
    0.08
    uropean
    0.08
    Activations Density 0.019%

    No Known Activations