© 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. 50582
    Prev
    Next
    INDEX
    Explanations

    detailed engineering and analysis

    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
    Ùī
    -0.09
    ä¸ĵèģĮ
    -0.08
    antha
    -0.08
    uhe
    -0.08
    fé
    -0.08
    roph
    -0.08
    åIJĦçķĮ
    -0.08
    rob
    -0.08
    igel
    -0.08
    å°ı游æĪı
    -0.08
    POSITIVE LOGITS
    ç»Ĩèĩ´
    0.10
    ied
    0.10
    涮
    0.10
    èĢĮåıĪ
    0.10
    çĬĬ
    0.10
     enough
    0.10
    lest
    0.10
    zie
    0.09
    ç¨ĭ度
    0.09
    约ä¼ļ
    0.09
    Activations Density 0.014%

    No Known Activations