© 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. 31830
    Prev
    Next
    INDEX
    Explanations

    prepositions and word endings

    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
    Ø£Ùĩد
    -0.08
    ÙħصÙĦØŃØ©
    -0.08
    æĢµ
    -0.08
    استÙĤÙĦ
    -0.08
    ÙħصاÙĦØŃ
    -0.07
    أغÙĦب
    -0.07
    ↵↵
    -0.07
    Spoiler
    -0.07
    Ø¥ÙĨØ´
    -0.07
     ATL
    -0.07
    POSITIVE LOGITS
    bai
    0.11
    â½£
    0.08
    INDER
    0.08
    RICS
    0.08
    åĽłä¸ºæĪij们
    0.08
    ⽤
    0.08
    â¾
    0.07
    ¦Ĥ
    0.07
    _startup
    0.07
    â¾ı
    0.07
    Activations Density 20.593%

    No Known Activations