© 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. 11562
    Prev
    Next
    INDEX
    Explanations

    forwarding information

    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
    ä¸Ģåı£
    -0.11
    èĸ®
    -0.10
    é«ĺç§ijæĬĢ
    -0.09
    acks
    -0.09
    æ²Ķ
    -0.09
     gắn
    -0.08
    ful
    -0.08
    带æĿ¥æĽ´å¤ļ
    -0.08
    æģ©
    -0.08
    åĽłä¸ºæĪij
    -0.08
    POSITIVE LOGITS
    ese
    0.10
    æ´Ļ
    0.10
    oga
    0.09
    สà¸Ķ
    0.08
    æĪĺåĽ½
    0.08
     kepada
    0.08
    å«ļ
    0.08
    æĪĺ
    0.08
    èIJ¥
    0.08
    nda
    0.08
    Activations Density 0.033%

    No Known Activations