© 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. 4264
    Prev
    Next
    INDEX
    Explanations

    Italy and places in Italy

    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
    kus
    -0.09
    åĩºåĶ®
    -0.08
    åĥŃ
    -0.08
    ROME
    -0.08
    éĥ½ä¼ļæľī
    -0.08
    ossal
    -0.08
    海绵
    -0.08
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    -0.08
     DRAW
    -0.08
    æ·±
    -0.08
    POSITIVE LOGITS
    ä¸įæŃ»
    0.09
    æݳ
    0.09
    举èIJ¥
    0.09
    ailing
    0.09
    éĺij
    0.08
    端
    0.08
    ÙĪاء
    0.08
    _Util
    0.08
    æĪį
    0.08
    licant
    0.08
    Activations Density 0.102%

    No Known Activations