© 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. 36048
    Prev
    Next
    INDEX
    Explanations

    license

    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
    bai
    -0.11
    â½£
    -0.08
    ⽤
    -0.08
    INDER
    -0.07
    RICS
    -0.07
    خت
    -0.07
    ¦Ĥ
    -0.07
    â¾
    -0.07
    â¾ı
    -0.07
    "class
    -0.06
    POSITIVE LOGITS
    ÙħصÙĦØŃØ©
    0.10
    Ø£Ùĩد
    0.10
    استÙĤÙĦ
    0.09
    åı¯æĥ³èĢĮçŁ¥
    0.09
    أغÙĦب
    0.09
    استÙģ
    0.09
    ÙĨتائ
    0.09
    ÙħصاÙĦØŃ
    0.09
    ÙħصÙĦ
    0.09
     سبØŃ
    0.09
    Activations Density 6.323%

    No Known Activations