© 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. 5971
    Prev
    Next
    INDEX
    Explanations

    seen many, seen a

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ä¼ĹæīĢ
    -0.09
    ç¹ģ
    -0.08
    è¯ķ
    -0.08
    çĶ³
    -0.08
     mer
    -0.08
    å±Ĭæ¯ķä¸ļçĶŁ
    -0.08
    çĨŁçŁ¥
    -0.08
    å·²ç»ıæľīäºĨ
    -0.08
    é«ĺå°Ķ
    -0.08
    Sele
    -0.08
    POSITIVE LOGITS
     myself
    0.10
     situations
    0.09
    让æĪij
    0.09
    è¿Ļæł·çļĦè¯Ŀ
    0.09
    èµĦæĸĻæĺ¾ç¤º
    0.08
    ãĤ¸ãĥ£ãĥ³
    0.08
     watch
    0.08
    èı½
    0.08
    زر
    0.08
    kus
    0.08
    Activations Density 0.093%

    No Known Activations