© 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. 40209
    Prev
    Next
    INDEX
    Explanations

    deposition techniques

    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
    ç©°
    -0.09
    æĺ¼
    -0.09
    çĺ«
    -0.09
    éķ¿çº¦
    -0.09
    erves
    -0.09
    _CONVERT
    -0.09
    orrh
    -0.09
    Movement
    -0.09
    ëıĮ
    -0.09
     Movement
    -0.09
    POSITIVE LOGITS
    åIJĮèĥŀ
    0.10
    æĬļ
    0.10
    ycl
    0.09
    æ²ī积
    0.09
    æĪIJéķ¿ä¸º
    0.08
    æ¶
    0.08
    éķĢ
    0.08
    åħ»æĪIJ
    0.08
    æ·Ģ
    0.08
    èIJ¥éĢł
    0.08
    Activations Density 0.418%

    No Known Activations