© 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. 56283
    Prev
    Next
    INDEX
    Explanations

    days and hours

    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
    æ¬łç¼º
    -0.10
    å¸IJ
    -0.09
    æ°ijéĸĵ
    -0.09
    å¿ħçĦ¶ä¼ļ
    -0.09
    没èĥ½
    -0.09
    大家ä¸Ģèµ·
    -0.09
    æ±īè¯Ń
    -0.08
    çļĦæĥħ绪
    -0.08
    æľªèĥ½
    -0.08
    chair
    -0.08
    POSITIVE LOGITS
    å®ŀæĥł
    0.10
    ajan
    0.09
    顾客
    0.09
    åĴĮæľįåĬ¡
    0.08
    rette
    0.08
    å¼Ģåĩº
    0.08
     getMenu
    0.08
     اÙĦض
    0.08
    ships
    0.08
    åľ°éģĵ
    0.08
    Activations Density 0.013%

    No Known Activations