© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52134
    Prev
    Next
    INDEX
    Explanations

    United States or United Kingdom

    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
    auss
    -0.08
    ãĥ¥ãĥ¼
    -0.08
    笼
    -0.08
    æİ¢éĻ©
    -0.08
    æIJ¬è¿IJ
    -0.08
     casing
    -0.08
    arian
    -0.08
    palette
    -0.07
    åŃĺè´§
    -0.07
    Creators
    -0.07
    POSITIVE LOGITS
    ä¸ĢæĬĬ
    0.09
    oard
    0.09
    è´¥
    0.09
    éĴĵé±¼
    0.08
    okit
    0.08
    涿
    0.08
    éĴ°
    0.08
    weg
    0.08
    çĶ¨éĩı
    0.08
    æĺī
    0.08
    Activations Density 0.322%

    No Known Activations