© 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. 10911
    Prev
    Next
    INDEX
    Explanations

    indefinite articles followed by nouns

    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
    azzi
    -0.10
    çĩİ
    -0.10
    quine
    -0.09
    æ·¡æ·¡çļĦ
    -0.09
    è¿Ļ件
    -0.09
    容å¿į
    -0.09
    åĨįä¹Łä¸į
    -0.09
     ÅŁÃ¶yle
    -0.09
    ç¥ŀåľ£
    -0.09
    以èī²
    -0.09
    POSITIVE LOGITS
    zelf
    0.09
    æīª
    0.09
    称ä¹ĭ
    0.08
    lar
    0.08
    loe
    0.08
    年纪
    0.08
    .PERMISSION
    0.08
    ector
    0.08
    çģµéŃĤ
    0.07
    æ´ĭ
    0.07
    Activations Density 0.100%

    No Known Activations