© 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. 30096
    Prev
    Next
    INDEX
    Explanations

    transportation or travel destinations

    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
    å¼ĢæĶ¾å¼ı
    -0.09
     лиÑĨа
    -0.09
    尾巴
    -0.09
    ãģĨãģ¡ãģ«
    -0.09
    åĬĽè¿ĺæĺ¯
    -0.09
    ä½İ声
    -0.09
    ç»ıå¼Ģ
    -0.09
    éĤ£ç§į
    -0.09
    æŁIJç§į
    -0.09
    missive
    -0.08
    POSITIVE LOGITS
    åĨī
    0.11
    åĨ¥
    0.09
    好åIJ§
    0.09
    å½¼
    0.09
    æ°´æºIJ
    0.09
    eler
    0.08
     from
    0.08
     &
    0.08
    -and
    0.08
     Altern
    0.08
    Activations Density 0.110%

    No Known Activations