© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 16689
    Prev
    Next
    INDEX
    Explanations

    sent a question or questionnaire

    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
    Negative Logits
    çŁŃ线
    -0.08
    æĭ§
    -0.08
     neat
    -0.08
    对æĪij
    -0.08
     Sunrise
    -0.08
     Scarborough
    -0.08
    亲æīĭ
    -0.08
    åĢ¨
    -0.08
    夸
    -0.08
    OCR
    -0.08
    POSITIVE LOGITS
    åı·åı¬
    0.16
    åIJ¸å¼ķæĽ´å¤ļ
    0.15
    åIJ¸å¼ķ
    0.14
    å¾ģéĽĨ
    0.14
    åIJ¸å¼ķäºĨ
    0.13
    æĭĽåĭŁ
    0.13
    åIJ¸å¼ķåĬĽ
    0.13
    åĬ¨åijĺ
    0.13
    éĤĢ请
    0.12
    åıijåĬ¨
    0.12
    Activations Density 0.286%

    No Known Activations