© 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. 22048
    Prev
    Next
    INDEX
    Explanations

    cyrillic words

    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
    hausen
    -0.08
    ictions
    -0.08
    éĩijçīĮ
    -0.08
    èį»
    -0.08
    неÑĢ
    -0.08
    ration
    -0.08
    ÑģÑĤавка
    -0.08
     Wallpaper
    -0.08
     ment
    -0.08
    天ä¸ĭ
    -0.07
    POSITIVE LOGITS
    çļĦ人çĶŁ
    0.14
     à¹Ĩ
    0.14
    çļĦå¿ĥ
    0.13
    çļĦæľįåĬ¡
    0.13
    çļĦæĬķèµĦ
    0.13
    çļĦéĢīæĭ©
    0.13
    à¹Ĩ
    0.12
    nya
    0.12
    çļĦçľ¼çĿĽ
    0.12
    çļĦå®īåħ¨
    0.12
    Activations Density 0.200%

    No Known Activations