© 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. 63929
    Prev
    Next
    INDEX
    Explanations

    mariners, win, names, ular

    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
    åıĮéĩį
    -0.10
    éŨå¤ĸ
    -0.09
    symbols
    -0.09
    èıĬ
    -0.09
    Streamer
    -0.09
    æijŀ
    -0.09
    çŁ¾
    -0.09
    اÙĨÙĬا
    -0.09
    INY
    -0.09
    æĹĭå¾ĭ
    -0.08
    POSITIVE LOGITS
    ãĥªãĥ³
    0.09
     Zub
    0.08
    оÑĩек
    0.08
    ondo
    0.08
    osite
    0.08
    lok
    0.08
     elaborate
    0.08
    æIJ¬
    0.08
    åĩŃ
    0.08
    æĨij
    0.08
    Activations Density 0.007%

    No Known Activations