© 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. 24191
    Prev
    Next
    INDEX
    Explanations

    emoticon or symbol markers

    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
    åĪ°ä½į
    -0.08
    å°±æĦıåij³çĿĢ
    -0.08
    æīĵéĢļ
    -0.08
    åijĬè¯īä»ĸ
    -0.08
    奴
    -0.08
    erness
    -0.08
    æ¸ħæĺİ
    -0.08
    arness
    -0.08
    esa
    -0.08
    opia
    -0.08
    POSITIVE LOGITS
    ç¬Ķ
    0.10
    неÑĨ
    0.09
    çŃĨ
    0.09
    æķ´çIJĨ
    0.09
    anske
    0.09
    é¦ĸåıij
    0.09
    ä¸Ģ对
    0.09
    ILT
    0.08
     Ingram
    0.08
     CPA
    0.08
    Activations Density 0.052%

    No Known Activations