© 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. 8325
    Prev
    Next
    INDEX
    Explanations

    rid/ine endings

    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
    éĶ¦ç»£
    -0.09
    æķ¬
    -0.09
    noch
    -0.08
    åĿļæĮģ
    -0.08
    oplan
    -0.08
    æ¾¹
    -0.08
    CLUD
    -0.08
    æĸ«
    -0.08
     mil
    -0.08
    orm
    -0.08
    POSITIVE LOGITS
    æĢĨ
    0.10
    åĸĥ
    0.09
    åĪºå®¢
    0.09
    嵩
    0.09
     sine
    0.09
     Miche
    0.08
    MEA
    0.08
    INE
    0.08
    åĹª
    0.08
    èĸľ
    0.08
    Activations Density 0.069%

    No Known Activations