© 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. 3431
    Prev
    Next
    INDEX
    Explanations

    need to

    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
    ADOR
    -0.09
     suá»ijt
    -0.08
    ãģĹãģĭ
    -0.08
    çĶŁæĢķ
    -0.08
    åIJĬ
    -0.08
    é©
    -0.08
    ä¸ĩä¸Ģ
    -0.08
     diluted
    -0.08
    Rub
    -0.08
    nic
    -0.08
    POSITIVE LOGITS
    å°ijä¸įäºĨ
    0.13
    åĮ»çĸĹæľºæŀĦ
    0.09
    åĴĢ
    0.09
    iev
    0.09
    HING
    0.09
    UCK
    0.09
    åīįåĪĹ
    0.08
     automobile
    0.08
    æĦıå¿Ĺ
    0.08
    æľ¬æĬ¥
    0.08
    Activations Density 0.031%

    No Known Activations