© 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. 56527
    Prev
    Next
    INDEX
    Explanations

    pedestrian crossings and accidents

    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
    éĻ·
    -0.11
    ç¾ģ
    -0.09
    åİŁæľī
    -0.09
    éĢIJ
    -0.09
    oney
    -0.08
    èµĦ
    -0.08
    éro
    -0.08
    å¤ļäºĨ
    -0.08
    errat
    -0.08
    éĦĤ
    -0.08
    POSITIVE LOGITS
    è¡Į人
    0.11
    Entered
    0.10
     pedestrians
    0.09
     pedestrian
    0.09
    åĽ´å¢Ļ
    0.09
    æ¾¹
    0.09
    æĹłæĥħ
    0.09
    sti
    0.09
    æł¡å¤ĸ
    0.09
    ç²¾ç¥ŀæĸĩæĺİ
    0.09
    Activations Density 0.066%

    No Known Activations