© 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. 26044
    Prev
    Next
    INDEX
    Explanations

    getting caught up in situations

    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
    æĥľ
    -0.10
    ifice
    -0.09
    ç»ĻæĤ¨
    -0.09
    æģķ
    -0.09
    延
    -0.09
    ritz
    -0.09
    èĩªåѦ
    -0.09
    æĪijä¸įæĥ³
    -0.09
    idot
    -0.09
    æľ¬åij¨
    -0.09
    POSITIVE LOGITS
    anch
    0.09
    æ´¾
    0.09
    çķĻå®Ī
    0.09
    arry
    0.09
    subj
    0.09
    ÑĢид
    0.09
    æ¯Ľ
    0.08
     обÑĭ
    0.08
     reim
    0.08
    çĭİ
    0.08
    Activations Density 0.046%

    No Known Activations