© 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. 10785
    Prev
    Next
    INDEX
    Explanations

    derivative followed by dates or "of"

    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
    åľ¨åĮĹ京
    -0.10
    槲
    -0.10
    åIJĦçľģ
    -0.09
    纽约
    -0.09
    æĶ¶ç´§
    -0.09
    ä¸ĸçķĮåIJĦåĽ½
    -0.09
    åľ¨åĽ½å¤ĸ
    -0.09
     NYC
    -0.09
    çĶ·æľĭåıĭ
    -0.09
    大éĻĨ
    -0.09
    POSITIVE LOGITS
    æľ¬åľ°
    0.11
    å¸Ĥæ°ij
    0.10
    åħ¨åİ¿
    0.09
    便æ°ij
    0.09
    ç»į
    0.09
     locally
    0.09
     county
    0.09
    county
    0.09
    æł¡
    0.09
     local
    0.09
    Activations Density 0.206%

    No Known Activations