© 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. 51288
    Prev
    Next
    INDEX
    Explanations

    New York Post

    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
     synonyms
    -0.09
    ä½Ĩæĺ¯å¦Ĥæŀľ
    -0.09
    åı¸
    -0.09
    roz
    -0.09
    æĤ¼
    -0.09
    zia
    -0.09
    æĸ°éĹ»ä¸Ńå¿ĥ
    -0.08
    oste
    -0.08
    åıĪèĥ½
    -0.08
    带走
    -0.08
    POSITIVE LOGITS
    èł¢
    0.09
    åłij
    0.09
    é£İåIJ¹
    0.08
    èĪĶ
    0.08
    å°±æѤ
    0.08
    /Framework
    0.08
    اط
    0.08
    æ°į
    0.08
    çļĦç¡®
    0.08
    åĴĦ
    0.08
    Activations Density 0.008%

    No Known Activations