© 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. 51447
    Prev
    Next
    INDEX
    Explanations

    ease and effortlessness

    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
    hurst
    -0.10
    ä¸į大
    -0.09
    avic
    -0.09
    pai
    -0.09
    严éĩį
    -0.08
    aras
    -0.08
    åĩ¿
    -0.08
    ivre
    -0.08
    nect
    -0.08
    ä¼Ļ
    -0.08
    POSITIVE LOGITS
    loom
    0.10
    åģļä¸įåĪ°
    0.09
    沦
    0.09
     Reb
    0.09
    çIJĨä¼ļ
    0.09
    æİ¥åIJ¬
    0.09
    å°Ĩèĩªå·±çļĦ
    0.08
    置身
    0.08
     Davies
    0.08
    大æ°Ķ
    0.08
    Activations Density 0.005%

    No Known Activations