© 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. 12173
    Prev
    Next
    INDEX
    Explanations

    take seriously or for granted

    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
    èµ°å¾Ĺ
    -0.10
    овÑĭй
    -0.08
    rose
    -0.08
    éĿ
    -0.08
    illary
    -0.08
    éĻĭ
    -0.08
    æłĹ
    -0.08
    물
    -0.08
     concern
    -0.08
    ailing
    -0.07
    POSITIVE LOGITS
    寤
    0.10
    åĪ°çİ°åľ¨
    0.10
    iaz
    0.09
    ढ
    0.09
    ä¸įå¾Ĺ转载
    0.09
    çİĩè¾¾åĪ°
    0.09
    ç®Ķ
    0.09
    못
    0.09
    èij±
    0.09
     ÙĦÙĦغاÙĬØ©
    0.09
    Activations Density 0.008%

    No Known Activations