© 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. 33025
    Prev
    Next
    INDEX
    Explanations

    business partners and providers

    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
    仪
    -0.11
     pé
    -0.09
    å²Ĺä½į
    -0.09
    xFFFFFFFF
    -0.09
     DIY
    -0.08
    æĶ¸
    -0.08
     Pinterest
    -0.08
    åĩ»
    -0.08
     prop
    -0.08
    æīĢåľ¨
    -0.08
    POSITIVE LOGITS
    éĹª
    0.11
    ç²¾éĢī
    0.10
    åIJĪä½ľä¼Ļä¼´
    0.10
    åħ¥é©»
    0.10
    æĬĺæī£
    0.09
    çĸµ
    0.09
    åħ¨é¢Ŀ
    0.09
     cục
    0.09
    å¤ļ家
    0.09
    agged
    0.08
    Activations Density 0.065%

    No Known Activations