© 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. 2511
    Prev
    Next
    INDEX
    Explanations

    asking why

    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
     zwar
    -0.10
    åĽłä¸ºä½ł
    -0.09
    èĩªä¸»
    -0.08
    ëªħ
    -0.08
     Pastor
    -0.08
    æ°¸è¿ľä¸įä¼ļ
    -0.08
    åĽłä¸ºä»ĸ
    -0.08
    สม
    -0.08
    ä½Ĩæĺ¯å¦Ĥæŀľ
    -0.08
     Compiled
    -0.08
    POSITIVE LOGITS
    ä»įæľī
    0.10
    åįİçĽĽé¡¿
    0.09
     Keystone
    0.09
    åIJİéĿ¢çļĦ
    0.09
    éģį
    0.09
    ipples
    0.09
    å®ł
    0.09
    樯
    0.09
    cant
    0.09
    лей
    0.08
    Activations Density 0.023%

    No Known Activations