© 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. 9974
    Prev
    Next
    INDEX
    Explanations

    certificate or agency report

    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
    çļĦ带é¢Ĩ
    -0.09
    èįŁ
    -0.09
    ERR
    -0.08
    äu
    -0.08
    éĶ¦
    -0.08
    abad
    -0.08
    atch
    -0.08
    æĪIJåĬŁçļĦ
    -0.08
    efined
    -0.08
    .nlm
    -0.08
    POSITIVE LOGITS
    è¯ģ书
    0.12
    éī´
    0.12
    åħ¬æŃ£
    0.12
    åĩºåħ·
    0.11
    éī´å®ļ
    0.11
    第ä¸īæĸ¹
    0.10
    ç»ĵ论
    0.10
     certificate
    0.10
    åķĨæĪ·
    0.09
    è¯Ħå®ļ
    0.09
    Activations Density 0.043%

    No Known Activations