© 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. 2744
    Prev
    Next
    INDEX
    Explanations

    believe that

    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
    ä¹ĭåĬ¿
    -0.09
    æį·
    -0.09
    ä¸Ģ群
    -0.08
    å°ĨæĿ¥
    -0.08
    ä¸Ĭãģ§
    -0.08
    ä¸į容æĺĵ
    -0.08
    æ¦Ħ
    -0.08
    å·®
    -0.08
     |_
    -0.08
    åħļåĴĮ
    -0.08
    POSITIVE LOGITS
    认为
    0.20
    ä»ĸ认为
    0.16
    èªįçĤº
    0.15
    ä¸»å¼ł
    0.15
     believe
    0.14
    éĥ½è®¤ä¸º
    0.12
     believes
    0.12
    åĿļä¿¡
    0.12
     belief
    0.12
    æĪij们认为
    0.11
    Activations Density 0.044%

    No Known Activations