© 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. 36911
    Prev
    Next
    INDEX
    Explanations

    trucking and transportation jobs

    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
    缴åįĩ
    -0.10
    çķĻåѦ
    -0.10
    åĪ«å¢ħ
    -0.10
    ç»Į
    -0.10
    éĺĴ
    -0.10
    uids
    -0.09
    åĪĴ
    -0.09
    èĬŁ
    -0.09
    æ³»
    -0.09
     quần
    -0.09
    POSITIVE LOGITS
    åį¡è½¦
    0.11
    æŁ´æ²¹
    0.11
    èIJ¥è¿IJ
    0.10
    éķ¿éĢĶ
    0.10
    ç½IJ
    0.10
    è£ħåį¸
    0.09
     diesel
    0.09
    fleet
    0.09
     truck
    0.09
    æĵį
    0.09
    Activations Density 0.126%

    No Known Activations