© 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. 59201
    Prev
    Next
    INDEX
    Explanations

    rat and ratifications

    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
    ãģĹãģ¾ãģĦ
    -0.11
    ï¸
    -0.11
    parator
    -0.09
    è¿Īåĩº
    -0.09
    bart
    -0.09
    ä¸Ģè§Ĵ
    -0.09
    绿水
    -0.08
    idas
    -0.08
    ãĥ£
    -0.08
    åľ³
    -0.08
    POSITIVE LOGITS
    ials
    0.10
    istic
    0.10
    ynch
    0.10
    ting
    0.09
    ãģĦãģı
    0.09
    ync
    0.08
    apult
    0.08
    媵
    0.08
     Cunning
    0.08
    poi
    0.08
    Activations Density 0.029%

    No Known Activations