© 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. 52210
    Prev
    Next
    INDEX
    Explanations

    god's word

    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
    çݹ
    -0.09
    lah
    -0.09
    Ī
    -0.09
    è®°å¿ĨåĬĽ
    -0.09
    éĥ½æĥ³
    -0.09
    è´´
    -0.08
    åģİ
    -0.08
    -driving
    -0.08
    lö
    -0.08
    æľŁåĨħ
    -0.08
    POSITIVE LOGITS
    lessly
    0.12
    éĴĬ
    0.11
    çĽ¸ä¼ł
    0.11
    åĻĮ
    0.10
    æĻļæĬ¥
    0.10
    æĪªåĽ¾
    0.09
     tắt
    0.09
    俵
    0.09
    istr
    0.09
    æķ´ä¸ªäºº
    0.09
    Activations Density 0.013%

    No Known Activations