© 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. 64000
    Prev
    Next
    INDEX
    Explanations

    time, labor, meat, love

    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
    éħ¢
    -0.09
     Berger
    -0.08
    enis
    -0.08
    缤
    -0.08
    obar
    -0.08
    OTT
    -0.08
    bery
    -0.08
    åij½
    -0.08
    _placement
    -0.08
    èĦ¸ä¸Ĭ
    -0.08
    POSITIVE LOGITS
    Miss
    0.09
    æŀ£
    0.09
    ieee
    0.09
     Ras
    0.09
     pur
    0.09
    éĴĬ
    0.09
    å²Ĥ
    0.09
    å±ij
    0.08
    ä»Ĺ
    0.08
    æ¡ĵ
    0.08
    Activations Density 0.096%

    No Known Activations