© 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. 52218
    Prev
    Next
    INDEX
    Explanations

    things that annoy you

    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
    为主çļĦ
    -0.09
    çĻ¾å®¶
    -0.09
    ç²¹
    -0.09
    æľīæĦı
    -0.09
     cháy
    -0.08
    hazi
    -0.08
    ãĥľãĥ¼
    -0.08
    ç½ijéĢļ
    -0.08
    ipc
    -0.08
    quirer
    -0.08
    POSITIVE LOGITS
    thin
    0.09
    berman
    0.09
    thing
    0.09
    æŁ´
    0.09
    æģĭ
    0.09
    omp
    0.08
    æģIJæĢķ
    0.08
    çľī
    0.08
    衲
    0.08
    è¿Ļéĥ¨
    0.08
    Activations Density 0.068%

    No Known Activations