© 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. 1794
    Prev
    Next
    INDEX
    Explanations

    thermoplastic polymer

    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
    ä¸Ģèĩ´
    -0.10
    头éĥ¨
    -0.09
    leaf
    -0.09
    اء
    -0.08
    人为
    -0.08
    stration
    -0.08
    æīĵåħ¥
    -0.08
    å®Į
    -0.08
    çłĶ究ä¸Ńå¿ĥ
    -0.08
    åı¶
    -0.08
    POSITIVE LOGITS
    æĹłéļľç¢į
    0.10
    èĪ£
    0.09
    yny
    0.09
    ful
    0.09
    ç»Ī
    0.08
    çĬĬ
    0.08
    Verb
    0.08
    parity
    0.08
    å¾Īæĺİæĺ¾
    0.08
     Shooting
    0.08
    Activations Density 0.091%

    No Known Activations