© 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. 32154
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives

    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
    UTO
    -0.09
    æ´Ļ
    -0.08
     Governors
    -0.08
    arr
    -0.08
    çľ¼åīįçļĦ
    -0.08
    å§ĭäºİ
    -0.08
    ube
    -0.08
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.08
    tas
    -0.08
     Shib
    -0.08
    POSITIVE LOGITS
    æµģæ°´
    0.09
    æľīèĥ½åĬĽ
    0.09
    åıĪæĺ¯
    0.09
    yah
    0.09
    å¾Īéĩįè¦ģ
    0.09
    åķ®
    0.08
    强æľīåĬĽçļĦ
    0.08
     non
    0.08
    placeholders
    0.08
    ä¸ŃåĽ½åĪ¶éĢł
    0.08
    Activations Density 0.116%

    No Known Activations