© 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. 5711
    Prev
    Next
    INDEX
    Explanations

    person concluding phrase

    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
    ç§įæ¤į
    -0.09
    ç¯Ŀ
    -0.09
    罨
    -0.08
    èѦåĬ¡
    -0.08
     assassin
    -0.08
    gems
    -0.08
    鸬
    -0.08
     girlfriends
    -0.08
     Physicians
    -0.08
     sake
    -0.08
    POSITIVE LOGITS
    人士
    0.23
    ä¹ĭ人
    0.20
     ngÆ°á»Ŀi
    0.18
    éĤ£ä½į
    0.17
    人ãģĮ
    0.16
    ä¸Ģä½į
    0.16
    人éĥ½
    0.16
    ä¸ĵä¸ļ人士
    0.16
    æ¯ıä¸Ģä½į
    0.15
    缸åħ³äººåijĺ
    0.15
    Activations Density 0.772%

    No Known Activations