© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9714
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases

    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
    以便
    -0.09
    heels
    -0.08
    éĥ¢
    -0.08
    年代
    -0.08
     heck
    -0.08
     Greene
    -0.08
    ä¹ĭå¤ľ
    -0.08
    åħ´è¶£
    -0.08
    æ²ī
    -0.08
     heav
    -0.08
    POSITIVE LOGITS
    æĸ¯é¡¿
    0.10
    iros
    0.10
    èµ·æĿ¥
    0.10
    åºĶä»ĺ
    0.09
    ä»ĸ说
    0.09
    à´´
    0.09
    ä¹Łåıªèĥ½
    0.09
     Berm
    0.09
    åIJ¬è¯´
    0.09
    æĵħèĩª
    0.09
    Activations Density 0.036%

    No Known Activations