© 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. 38335
    Prev
    Next
    INDEX
    Explanations

    ownership

    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
    ÑĩаÑĤ
    -0.12
    é¼ĵèĪŀ
    -0.10
    çĹ¼
    -0.09
    议论
    -0.09
    -bel
    -0.09
    çĶŁäº§åĬĽ
    -0.09
    ä¸īæĿ¡
    -0.09
    éĿĻèĦī
    -0.09
    åķĨåĬ¡
    -0.08
    æĪij们åı¯ä»¥
    -0.08
    POSITIVE LOGITS
    度
    0.09
    å¨ĺ
    0.09
     bow
    0.09
    ini
    0.08
    prü
    0.08
    esp
    0.08
    trys
    0.08
     наÑģелениÑı
    0.08
    è¿ĻçĤ¹
    0.08
    elter
    0.08
    Activations Density 0.006%

    No Known Activations