© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10477
    Prev
    Next
    INDEX
    Explanations

    comparative and additive statements

    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
    atory
    -0.09
    Ñĩем
    -0.09
    å¾®å¦Ļ
    -0.08
    æĬ
    -0.08
    鼷æĸ¯
    -0.08
    究
    -0.08
    lw
    -0.08
     vö
    -0.08
    éĺ»åĬĽ
    -0.08
    usty
    -0.08
    POSITIVE LOGITS
    äº²çľ¼
    0.09
    appen
    0.09
    第äºĮæī¹
    0.09
    æĦ¦
    0.08
    ä¸Ģç¯ĩ
    0.08
    åºĶæĶ¶
    0.08
    ighth
    0.08
    é«ĺåħ´
    0.08
    (td
    0.08
    æķ´ä¸ªäºº
    0.08
    Activations Density 0.004%

    No Known Activations