© 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. 8409
    Prev
    Next
    INDEX
    Explanations

    cruises, grapes, acid, limestone, chateau, viticulture, wine

    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
    ograd
    -0.10
    åıĮåıĮ
    -0.10
    çĽijçĿ£æ£ĢæŁ¥
    -0.09
    stown
    -0.09
    奶
    -0.09
    å°±åºĶ该
    -0.09
    èĬĤ
    -0.09
    rimp
    -0.09
    resco
    -0.09
    èį¡
    -0.08
    POSITIVE LOGITS
    çݰ身
    0.10
    èįĴ
    0.10
     Carnegie
    0.10
    çªľ
    0.09
    åĿ¡
    0.09
    å£ķ
    0.08
    å¾Ĺ好
    0.08
    биÑĤ
    0.08
    æĬ¬å¤´
    0.08
    Axes
    0.08
    Activations Density 0.033%

    No Known Activations