© 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. 40358
    Prev
    Next
    INDEX
    Explanations

    retail store names

    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
     coc
    -0.09
    åĮºåĿĹ
    -0.09
    mö
    -0.09
    åIJĪçIJĨçļĦ
    -0.09
    _plugins
    -0.09
    .sdk
    -0.09
    纷
    -0.09
     Coc
    -0.09
    黳
    -0.09
    纵
    -0.08
    POSITIVE LOGITS
    è¿ŀéĶģ
    0.10
    åĵij
    0.09
    _VEC
    0.09
    replacement
    0.09
    æĥłæ°ij
    0.09
    Ñģо
    0.08
    ä¿¡çĶ¨
    0.08
    æį¢äºĨ
    0.08
     Pharmacy
    0.08
    线ä¸Ĭ线ä¸ĭ
    0.08
    Activations Density 0.152%

    No Known Activations