© 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. 16651
    Prev
    Next
    INDEX
    Explanations

    noise or noise pollution

    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
    åĢª
    -0.10
    à¹Į
    -0.09
    innen
    -0.09
    ivers
    -0.09
    æŨ
    -0.08
    åŁ¤
    -0.08
    ä¸įäºĨ
    -0.08
    thood
    -0.08
    çİ
    -0.08
    ickness
    -0.08
    POSITIVE LOGITS
    speaker
    0.09
    lessly
    0.09
    åĸ§
    0.09
    ful
    0.08
    æģª
    0.08
    أت
    0.08
    åĺ¶
    0.08
    обÑĢаÐ
    0.08
    ored
    0.08
    éªħ
    0.08
    Activations Density 0.012%

    No Known Activations