© 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. 34839
    Prev
    Next
    INDEX
    Explanations

    lost and found; reunion

    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
    ä¼ı
    -0.11
    ä»ĵ
    -0.09
    æĦģ
    -0.09
    æĦļ
    -0.09
    HEME
    -0.09
    ä¸į说
    -0.09
    åĢ¾æĸľ
    -0.09
    èººåľ¨åºĬä¸Ĭ
    -0.09
    éĢĴ
    -0.09
    丼
    -0.09
    POSITIVE LOGITS
    æī¾åĽŀ
    0.16
    失踪
    0.13
     reunion
    0.13
     reun
    0.12
     reunited
    0.12
    åĽ¢åľĨ
    0.12
    丢失
    0.12
     Lost
    0.12
     lost
    0.11
    Lost
    0.11
    Activations Density 0.096%

    No Known Activations