© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 23306
    Prev
    Next
    INDEX
    Explanations

    save, backup, data, store

    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
    ä¼ģä¸ļæıIJä¾Ľ
    -0.11
    æºIJæºIJä¸įæĸŃ
    -0.11
    æŃª
    -0.10
    滥
    -0.10
    ç¦ģ
    -0.10
    èı²å°Ķ
    -0.10
    秫
    -0.10
     kı
    -0.10
    entai
    -0.10
    ä¸Ģ个éĹ®é¢ĺ
    -0.10
    POSITIVE LOGITS
    æī¿
    0.11
    åĤ¨èĵĦ
    0.10
     loss
    0.10
    åŃĺ
    0.10
     saving
    0.09
    å¤ĩ份
    0.09
     save
    0.09
    store
    0.09
    æĬĴ
    0.09
     saves
    0.09
    Activations Density 0.091%

    No Known Activations