© 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. 11073
    Prev
    Next
    INDEX
    Explanations

    Russian and English mixed language

    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
    å¼ĤæĢ§
    -0.09
    öt
    -0.09
    ÑıÑīиÑħ
    -0.09
     dziaÅĤania
    -0.09
    çĽ¸ä¼¼
    -0.08
    cert
    -0.08
    éĢIJ
    -0.08
    åħ¬ç¤º
    -0.08
    çľ¼éĩĮ
    -0.08
    ansas
    -0.08
    POSITIVE LOGITS
     поÑĩем
    0.10
    ç§ķ
    0.09
    kip
    0.09
     подÑĢобн
    0.09
     ÑģлиÑĪ
    0.09
    åľ¨æĪijçļĦ
    0.09
     даж
    0.09
    éħį
    0.08
     ÑĢанÑĮ
    0.08
    ä¸į好æĦıæĢĿ
    0.08
    Activations Density 0.217%

    No Known Activations