© 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. 16668
    Prev
    Next
    INDEX
    Explanations

    title/name suffix

    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
    å°¤åħ¶æĺ¯åľ¨
    -0.13
    çī¹åĪ«æĺ¯åľ¨
    -0.11
    æ¯ĶåĪ©
    -0.10
    æĸ°å¨ĺ
    -0.10
    è®°å¾Ĺ
    -0.10
    èĢģçĪ·åŃIJ
    -0.10
    éĩı产
    -0.10
    çĶ·äºº
    -0.10
    éķ¿ä¸īè§Ĵ
    -0.09
    娣
    -0.09
    POSITIVE LOGITS
    ä¸Ńå¿ĥ
    0.10
    owie
    0.10
    骨干
    0.09
    หาร
    0.09
    bury
    0.09
     formerly
    0.08
    æĺĶæĹ¥
    0.08
    åĬŁåĬĽ
    0.08
    å®ŀè´¨
    0.08
     Jr
    0.08
    Activations Density 0.194%

    No Known Activations