© 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. 8638
    Prev
    Next
    INDEX
    Explanations

    copyright or ington ending

    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
    åºķèķ´
    -0.09
    æĢľ
    -0.09
    åĽ½éģĵ
    -0.09
    è¶Ĭé«ĺ
    -0.09
    ffer
    -0.08
    å¾Ĺä½ı
    -0.08
    hos
    -0.08
     Tess
    -0.08
     mer
    -0.08
    åıĤè°ĭ
    -0.08
    POSITIVE LOGITS
    大家ä¸Ģèµ·
    0.09
    ular
    0.09
    eming
    0.08
    år
    0.08
    两家
    0.08
    ally
    0.08
    éĶĹ
    0.08
    anz
    0.08
    igli
    0.08
    åĶ¾
    0.08
    Activations Density 0.002%

    No Known Activations