© 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. 1849
    Prev
    Next
    INDEX
    Explanations

    master suite or guest bathroom

    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
    å½¼
    -0.10
    稿
    -0.09
    sole
    -0.08
    ä¸ĢéĹª
    -0.08
    asers
    -0.08
    èĢ¸
    -0.08
    å¼Ģåı£
    -0.08
    обÑĢаз
    -0.08
    vehicles
    -0.08
     haus
    -0.08
    POSITIVE LOGITS
    æ¿ķ
    0.09
    оÑĩ
    0.09
    çļĦæĦ¿æľĽ
    0.09
    -packages
    0.09
    æĪIJ绩åįķ
    0.09
    ientes
    0.09
    ä¸įæ¸ħ
    0.09
     Feather
    0.08
    ç¾İ好çĶŁæ´»
    0.08
    è´¨éĩıåĴĮ
    0.08
    Activations Density 0.003%

    No Known Activations