© 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. 9052
    Prev
    Next
    INDEX
    Explanations

    proceed with

    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
    å®īç½®
    -0.09
    atoon
    -0.09
     domic
    -0.09
    berger
    -0.09
    matic
    -0.09
    åĢ¼å¾Ĺä¸Ģ
    -0.09
    å²Ļ
    -0.08
    æIJĢ
    -0.08
     reinc
    -0.08
    ized
    -0.08
    POSITIVE LOGITS
    çݰ象
    0.10
     phenomenon
    0.10
     mentality
    0.10
    çļĦå±ĢéĿ¢
    0.10
    åİŁåĪĻ
    0.09
    çļĦæĥħå½¢
    0.09
    å±ĢéĿ¢
    0.09
    æĦıåij³
    0.09
    æĥħå½¢
    0.08
    illions
    0.08
    Activations Density 0.183%

    No Known Activations