© 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. 17805
    Prev
    Next
    INDEX
    Explanations

    program production or purchases

    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
    缴æĴŃéĹ´
    -0.11
    ä¸ĵä¸ļä»İäºĭ
    -0.09
    åįİ润
    -0.09
    åIJ¬å®Į
    -0.09
    iquer
    -0.09
    客车
    -0.09
    åĽŀåij³
    -0.08
     Crush
    -0.08
    éĤ¦
    -0.08
    åħij
    -0.08
    POSITIVE LOGITS
    çĬĴ
    0.09
    骡
    0.09
    ä¸ĭä¸Ģ代
    0.09
     ongoing
    0.08
    ä¸Ģ款
    0.08
    éĿĴçĿIJ
    0.08
    æĸ°æ¬¾
    0.08
    ngoing
    0.08
    æŁ
    0.08
     Mobility
    0.08
    Activations Density 0.044%

    No Known Activations