© 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. 58658
    Prev
    Next
    INDEX
    Explanations

    categories and groups

    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
     Owens
    -0.09
    è¿Ļæł·ä¸Ģ个
    -0.08
    ãĥĭãĤ¢
    -0.08
     Synthetic
    -0.08
    åIJĮè¡Į
    -0.08
    fps
    -0.08
    STYPE
    -0.08
    imen
    -0.08
     compromise
    -0.08
     methodology
    -0.08
    POSITIVE LOGITS
    åĪĨåĪ«ä¸º
    0.17
    åĪĨåĪ«æĺ¯
    0.17
    åIJĦèĩªçļĦ
    0.16
     respectively
    0.15
    åĪĨåĪ«
    0.15
     respective
    0.14
    è¿Ļ两个
    0.13
    åĪĨåĪ¥
    0.13
    åIJĦèĩª
    0.12
    åıĮåıĮ
    0.12
    Activations Density 0.319%

    No Known Activations