© 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. 57888
    Prev
    Next
    INDEX
    Explanations

    collaboration and partnerships

    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
    æĩĴ
    -0.09
    ç»´æĿĥ
    -0.08
    æī¹
    -0.08
    è¿«
    -0.08
    åĪĿ级
    -0.08
     Merrill
    -0.08
    å¸Ĥåľºä»·æł¼
    -0.08
     минималÑĮ
    -0.08
    DCF
    -0.08
    asive
    -0.08
    POSITIVE LOGITS
    ç§ijçłĶ
    0.13
    ç§ijåŃ¦å®¶
    0.13
    产åѦçłĶ
    0.11
    éĽĨèģļ
    0.11
    ç§ijçłĶéĻ¢
    0.11
    åѵ
    0.10
    çłĶåıij
    0.10
    åѵåĮĸ
    0.10
    产ä¸ļéĽĨ群
    0.10
    çłĶåıijæĬķåħ¥
    0.10
    Activations Density 0.138%

    No Known Activations