© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 12315
    Prev
    Next
    INDEX
    Explanations

    journey

    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
    Negative Logits
    æĸĩ娱
    -0.08
    Deprecated
    -0.08
    erville
    -0.08
    个å°ıæŶ
    -0.08
    ä¸įä¸Ĭ
    -0.08
    å¼ĤæĢ§
    -0.08
    éĺĬ
    -0.08
    æł¸å¿ĥ
    -0.08
    ansom
    -0.08
     [&
    -0.08
    POSITIVE LOGITS
     journey
    0.23
    æĹħç¨ĭ
    0.19
     Journey
    0.17
    å¾ģç¨ĭ
    0.17
    åİĨç¨ĭ
    0.16
    jour
    0.16
     journeys
    0.15
    æĹħéĢĶ
    0.15
    ä¹ĭæĹħ
    0.14
    ä¹ĭè·¯
    0.13
    Activations Density 0.059%

    No Known Activations