© 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. 29729
    Prev
    Next
    INDEX
    Explanations

    Facebook page or feed

    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
    Not in Any Lists

    No Comments

    Negative Logits
    èµ°è·¯
    -0.09
     Somerset
    -0.08
     Smy
    -0.08
    èµ°å¾Ĺ
    -0.08
     Bowman
    -0.08
     Middle
    -0.08
    è¾ij
    -0.08
    ä¸ĸéĹ´
    -0.08
    çľĩ
    -0.08
    ãĥĹãĥ©ãĤ¹
    -0.08
    POSITIVE LOGITS
    ROP
    0.10
    åĭĴ
    0.09
    poke
    0.09
    mv
    0.08
    /facebook
    0.08
    urette
    0.08
    aption
    0.08
    æĬķèµĦé¢Ŀ
    0.08
    tail
    0.08
    /email
    0.08
    Activations Density 0.028%

    No Known Activations