© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22095
    Prev
    Next
    INDEX
    Explanations

    tallest, oldest, largest, most

    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
    éĩįè¦ģåĨħ容
    -0.11
    æľ¬ç½ijç«Ļ
    -0.10
    æĻı
    -0.10
    åĬĪ
    -0.10
    çķĻè¨ĢæĿ¿
    -0.09
    åıįæĬĹ
    -0.09
     Medium
    -0.09
    廪
    -0.09
    亲åĪĩ
    -0.09
    æĸ°åħ´äº§ä¸ļ
    -0.09
    POSITIVE LOGITS
    ä¸ĸçķĮä¸Ĭ
    0.12
    ä¸ĸçķĮä¸ĬæľĢ
    0.11
    ä¸ĸä¸Ĭ
    0.10
    1
    0.10
    mma
    0.10
     ever
    0.10
    åħ¨ä¸ĸçķĮ
    0.09
    å·§
    0.09
    2
    0.09
    åĿ¤
    0.09
    Activations Density 0.145%

    No Known Activations