© 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. 30150
    Prev
    Next
    INDEX
    Explanations

    percentage of patients

    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
    éªĪ
    -0.10
    å°ijéĩı
    -0.09
    yal
    -0.09
     Rash
    -0.09
    çĤĬ
    -0.08
    è¾¹
    -0.08
    å°ij许
    -0.08
    ä¹Łåı¯èĥ½
    -0.08
    æĥħæĢĢ
    -0.08
    èĭ¥å¹²
    -0.08
    POSITIVE LOGITS
    大éĥ¨åĪĨ
    0.14
    ä¸īåĪĨ
    0.14
    ç»Ŀ大éĥ¨åĪĨ
    0.13
    ç»Ŀ大å¤ļæķ°
    0.13
    ä¸ĢåįĬ
    0.12
     majority
    0.12
    å¤ļæķ°
    0.11
     Majority
    0.11
    åįł
    0.11
    éĥ¨ä»½
    0.10
    Activations Density 0.192%

    No Known Activations