© 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. 64056
    Prev
    Next
    INDEX
    Explanations

    new items added weekly/daily

    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
    çŀ»
    -0.09
    Ãłi
    -0.08
    /rc
    -0.08
    çĤ¹åįĬ
    -0.08
    .Desc
    -0.08
    à¹Ģà¸ĸ
    -0.08
    åħ¨æ°ij
    -0.08
    æĭ¿äºĨ
    -0.08
    åį«çĶŁ
    -0.08
    InputBorder
    -0.08
    POSITIVE LOGITS
    ä¸įæĸŃå¢ŀåĬł
    0.10
    ou
    0.09
    éĤij
    0.08
     Hou
    0.08
    oi
    0.08
    ä¸įæĸŃåıijå±ķ
    0.08
    ooks
    0.08
    å¤©åºľ
    0.08
    tro
    0.08
    çĵ¯
    0.08
    Activations Density 0.022%

    No Known Activations