© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20581
    Prev
    Next
    INDEX
    Explanations

    trip planning

    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
    宾é¦Ĩ
    -0.09
    stro
    -0.09
    arf
    -0.08
    ims
    -0.08
    äºĮæľŁ
    -0.08
    è¨Ģ
    -0.08
    主æīĵ
    -0.08
    åıĺ为
    -0.08
    æİ¥åĬĽ
    -0.08
    è°´
    -0.08
    POSITIVE LOGITS
     trip
    0.10
    åĿ¨
    0.10
    æĿŁ
    0.10
    æĸ°ä¸ļæĢģ
    0.10
    ä¹ĺ客
    0.10
    trip
    0.09
    æ±IJ
    0.09
    èĻ¹
    0.09
    TRL
    0.09
    åĩºè¡Į
    0.09
    Activations Density 0.074%

    No Known Activations