© 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. 18736
    Prev
    Next
    INDEX
    Explanations

    And followed by clause

    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
    åĴĮæĬĢæľ¯
    -0.10
    éĤ£è¾¹
    -0.10
    è¾į
    -0.09
    éĤ£æŶ
    -0.09
    åĵģ
    -0.09
     Tide
    -0.09
    ä¸į满æĦı
    -0.09
     And
    -0.09
    å½¼
    -0.09
    ILING
    -0.08
    POSITIVE LOGITS
    èIJİ缩
    0.08
    æŀ¸æĿŀ
    0.08
    ç¨įç¨į
    0.08
    éĢŀ
    0.08
     Lawson
    0.08
     crow
    0.08
    ham
    0.08
    crow
    0.08
    -La
    0.07
    ç²¾åįİ
    0.07
    Activations Density 0.131%

    No Known Activations