© 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. 7147
    Prev
    Next
    INDEX
    Explanations

    names of people

    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
    å°ıåŃIJ
    -0.12
    çİĭåħĪçĶŁ
    -0.10
    åĴĮå°ļ
    -0.10
    å¼¢
    -0.10
    åĵ¥ä»¬
    -0.10
    å¼ŁåħĦ
    -0.09
    å°ıä¼ĻåŃIJ
    -0.09
     himself
    -0.09
    å¸ħæ°Ķ
    -0.09
    å¸ħ
    -0.09
    POSITIVE LOGITS
    她
    0.15
    她çļĦ
    0.14
    她说
    0.14
    ä½Ĩ她
    0.13
    å¥¹åľ¨
    0.13
     herself
    0.12
     she
    0.12
    她æĺ¯
    0.11
    æĬĬ她
    0.11
    她们
    0.10
    Activations Density 0.338%

    No Known Activations