© 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. 22521
    Prev
    Next
    INDEX
    Explanations

    negative connotations

    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
    ç²¹
    -0.09
    è¿ijæľŁ
    -0.08
    ateg
    -0.08
    ÙĥÙģ
    -0.08
    ategory
    -0.08
    çªģåĩ»
    -0.08
    Ø®ÙĬ
    -0.08
     даннÑĭй
    -0.08
    墩
    -0.08
    ä¸ĢåĽ¢
    -0.08
    POSITIVE LOGITS
    è¿Ń
    0.14
    ãĤº
    0.11
    æģĻ
    0.11
    äºĭåĦ¿
    0.11
    ity
    0.10
    estre
    0.10
    ellaneous
    0.10
    ä¹ĭå¤Ħ
    0.10
    ä¹ĭä½ľ
    0.10
    çİ©æĦı
    0.09
    Activations Density 0.006%

    No Known Activations