© 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. 48176
    Prev
    Next
    INDEX
    Explanations

    overview of topics

    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
     Osw
    -0.09
    çĸıæķ£
    -0.09
    æį£
    -0.09
    çĮ±
    -0.09
    éĻħ
    -0.09
    å²IJ
    -0.08
    æ´
    -0.08
    欧éĺ³
    -0.08
    è¿ŀ线
    -0.08
    ç©Ĺ
    -0.08
    POSITIVE LOGITS
    大å±Ģ
    0.10
    OfFile
    0.10
    ä¸Ģè§Ī
    0.10
    绣
    0.09
    è§Ī
    0.09
    views
    0.09
    èĤ©
    0.09
     Overview
    0.09
     overview
    0.09
    еÑĤÑĮ
    0.09
    Activations Density 0.039%

    No Known Activations