© 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. 47537
    Prev
    Next
    INDEX
    Explanations

    later, eventually, become

    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
    è¾ĵäºĨ
    -0.09
    è³¢
    -0.09
    Bay
    -0.09
    éĴĬ
    -0.09
    .ERR
    -0.09
    éĤ£åĦ¿
    -0.09
    è´¤
    -0.09
    _parm
    -0.08
    æ¸Ķ
    -0.08
    åıĻ
    -0.08
    POSITIVE LOGITS
    åIJİæĿ¥
    0.15
     later
    0.13
    later
    0.11
    å¾Įä¾Ĩ
    0.10
    Later
    0.10
     später
    0.10
     Later
    0.10
     eventual
    0.09
    unde
    0.09
     eventually
    0.09
    Activations Density 0.041%

    No Known Activations