© 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. 37981
    Prev
    Next
    INDEX
    Explanations

    radio therapy

    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
     nond
    -0.10
    èģĬ
    -0.08
    ibs
    -0.08
    大åºĨ
    -0.08
    æĤ¬æĮĤ
    -0.08
    é»Ħæ²³
    -0.08
    Soup
    -0.08
    çªĦ
    -0.08
    åĴı
    -0.08
    ISC
    -0.08
    POSITIVE LOGITS
    æ³¾
    0.10
    åıŃ
    0.09
    alia
    0.09
    erot
    0.09
     Maher
    0.09
    entai
    0.09
     Spi
    0.09
    ä¸įèī¯ä¿¡æģ¯
    0.09
    ç¢ī
    0.09
     Mana
    0.09
    Activations Density 0.497%

    No Known Activations