© 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. 60613
    Prev
    Next
    INDEX
    Explanations

    street names and locations

    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
    æĺķ
    -0.10
     Moto
    -0.10
    é¹Ĭ
    -0.09
    åī¯æł¡éķ¿
    -0.09
    æł¡éķ¿
    -0.09
    æ·¡æ·¡çļĦ
    -0.09
    å®ļçĤ¹
    -0.09
    æ¸ij
    -0.09
    ç¬Ī
    -0.09
    berger
    -0.08
    POSITIVE LOGITS
    CBD
    0.10
     street
    0.09
     CBD
    0.09
    è¡Ĺ头
    0.08
     Hague
    0.08
    instr
    0.08
    路人
    0.08
    street
    0.08
     tér
    0.08
     phá»ij
    0.08
    Activations Density 0.109%

    No Known Activations