© 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. 20020
    Prev
    Next
    INDEX
    Explanations

    nuclear tests

    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
     unc
    -0.10
    orc
    -0.10
    éĵĬ
    -0.09
    æľŁ
    -0.09
     unanimous
    -0.09
    é½IJ
    -0.09
    ULK
    -0.09
    å®Ī
    -0.09
    ä¾Ľæ±Ĥ
    -0.09
    leans
    -0.08
    POSITIVE LOGITS
    çĻ½çĻ½
    0.09
    çŁ¿åĮº
    0.09
     lat
    0.09
    lat
    0.09
     ringing
    0.08
    è¿ĺæľª
    0.08
    åºķä¸ĭ
    0.08
     playground
    0.08
    åįĥä¸ĩ
    0.08
    åĭĺæİ¢
    0.08
    Activations Density 0.051%

    No Known Activations