© 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. 58394
    Prev
    Next
    INDEX
    Explanations

    biological processes and structures

    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
    è¾ī
    -0.09
    使å¾Ĺ
    -0.08
    åį¿
    -0.08
    å°±æĬĬ
    -0.08
    amazon
    -0.08
    å°¤åħ¶
    -0.08
     phon
    -0.08
    å©¢
    -0.07
    èĬ±äºĨ
    -0.07
    åķĨ
    -0.07
    POSITIVE LOGITS
    éģ¸ãģ³
    0.12
    èĤ´
    0.10
    éĹ´çļĦ
    0.10
    éĿ¢èī²
    0.09
    æŀĭ
    0.09
    icates
    0.09
    æĸ°æµªè´¢ç»ı
    0.09
    å¤ļãģı
    0.09
    éıĬ
    0.09
    ä¹ĭéĹ´çļĦ
    0.09
    Activations Density 0.589%

    No Known Activations