© 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. 61347
    Prev
    Next
    INDEX
    Explanations

    Yes, I, we

    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©´
    -0.09
    贵宾
    -0.09
    æīĢ说çļĦ
    -0.09
    åįłé¢Ĩ
    -0.09
    é»Ħéĩij
    -0.09
    éĻ¤æѤ
    -0.08
    æĪijçĪ±ä½ł
    -0.08
    åıĤåĬłä¼ļè®®
    -0.08
    atab
    -0.08
     Eis
    -0.08
    POSITIVE LOGITS
    èįī
    0.10
    çĿĢ
    0.08
    ÙģÙĪر
    0.08
    olly
    0.08
    俯
    0.08
    uby
    0.08
    è¶Ĭæĺ¯
    0.08
    defgroup
    0.08
    ä¼Ļ
    0.08
    _vue
    0.08
    Activations Density 0.026%

    No Known Activations