© 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. 48650
    Prev
    Next
    INDEX
    Explanations

    limited editions or sales numbers

    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
    ereo
    -0.09
     fod
    -0.08
     Hick
    -0.08
    éĩį温
    -0.08
    å±Ĥ次
    -0.08
     Swift
    -0.08
    èħ¥
    -0.08
    /--
    -0.08
    å¤ĸç±į
    -0.08
    æݬ
    -0.08
    POSITIVE LOGITS
    ç¬ijèĦ¸
    0.09
    个ä½ĵ
    0.09
    çĤ¹ç¼Ģ
    0.09
    ä½ĵè´¨
    0.09
    龸çİĭ
    0.09
    /cop
    0.08
    åıijåĶ®
    0.08
    榨
    0.08
    é¦Ļæ°´
    0.08
    éĻĨç»Ń
    0.08
    Activations Density 0.091%

    No Known Activations