© 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. 49169
    Prev
    Next
    INDEX
    Explanations

    distribution systems, pipes, and lines

    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
    èħ¿éĥ¨
    -0.09
    rieb
    -0.09
    NIC
    -0.09
    èºģ
    -0.09
    wä
    -0.09
    çĶµæºIJ
    -0.08
    ä½ĨçĶ±äºİ
    -0.08
    è´
    -0.08
    ç«Ļéķ¿
    -0.08
    åģľçĶµ
    -0.08
    POSITIVE LOGITS
    ç³»ç»Ł
    0.11
    éģįå¸ĥ
    0.11
     network
    0.10
    ç³»ç»ŁçļĦ
    0.10
     system
    0.10
     sistem
    0.09
    etwork
    0.09
    åĪĨæĶ¯
    0.09
    å¸ĥå±Ģ
    0.09
    ä½ĵç³»
    0.09
    Activations Density 0.150%

    No Known Activations