© 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. 31971
    Prev
    Next
    INDEX
    Explanations

    meaning of words

    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
    ç½®
    -0.10
    æĪijåıijçİ°
    -0.09
    çĵ¦
    -0.09
    ãģĮãĤī
    -0.09
    æĹłåĬĽ
    -0.09
    æĦģ
    -0.09
    ç¦Ģ
    -0.08
    ä¸įåłª
    -0.08
    èĶº
    -0.08
    _fact
    -0.08
    POSITIVE LOGITS
     meant
    0.11
    çļĦéĤ£ç§į
    0.10
    è¿Ļè¯Ŀ
    0.09
    ä¹Łèĥ½
    0.09
    æĦıæĢĿæĺ¯
    0.08
    éĺ´éĺ³
    0.08
    ä¼ļéĢīæĭ©
    0.08
    èĪ£
    0.08
    rios
    0.08
    åħĭæĸ¯
    0.08
    Activations Density 0.039%

    No Known Activations