© 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. 50617
    Prev
    Next
    INDEX
    Explanations

    starting with "words"

    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
     Minority
    -0.09
    å¤ķ
    -0.08
     Morton
    -0.08
    RF
    -0.08
    åħ¨ç¨ĭ
    -0.08
    à¸Ľà¸£à¸°à¸Ĭาà¸Ĭà¸Ļ
    -0.08
    å°±æĺ¯ä¸ºäºĨ
    -0.08
    Charlotte
    -0.07
    趣
    -0.07
    èĬĴ
    -0.07
    POSITIVE LOGITS
    åıªèĥ½è¯´
    0.15
    è¦ģ说
    0.12
    èµŀèªī
    0.10
    è¤Ĵ
    0.10
    åĨį说
    0.10
    ä¸įå¾Ĺä¸į说
    0.10
    åı¯æĥ³
    0.10
    è¿Ļ个åIJįåŃĹ
    0.09
    æĬĬè¿Ļ个
    0.09
    ä¸Ģåı¥è¯Ŀ
    0.09
    Activations Density 0.027%

    No Known Activations