© 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. 21117
    Prev
    Next
    INDEX
    Explanations

    song titles or album titles

    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
    ÙĬÙĪ
    -0.08
     Revel
    -0.07
    容
    -0.07
    æ¦ķ
    -0.07
    åľ¨è¿ĻéĩĮ
    -0.07
     yö
    -0.07
     Kou
    -0.07
    hx
    -0.07
    大大å°ı
    -0.07
    大éĩıçļĦ
    -0.07
    POSITIVE LOGITS
    ä¹Łä¸įä¾ĭå¤ĸ
    0.14
    asel
    0.11
    /from
    0.11
    好è¿IJ
    0.10
    èĦ±
    0.09
    æĢİä¹ĪåĽŀäºĭ
    0.09
    .appspot
    0.09
    meye
    0.09
    äºĭåĦ¿
    0.09
    ä¸ĢåĽŀäºĭ
    0.09
    Activations Density 0.173%

    No Known Activations