© 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. 19200
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    åĨľçī§
    -0.08
     ÑħоÑĤÑĮ
    -0.08
     prim
    -0.07
    主è¦ģæĺ¯
    -0.07
    .ALIGN
    -0.07
    çī§
    -0.07
    ↵↵
    -0.07
    ialis
    -0.07
     har
    -0.07
    ä¸ĢèĪ¬æĺ¯
    -0.06
    POSITIVE LOGITS
    æīįç®Ĺ
    0.10
    æīįæĺ¯
    0.10
    æī«ä¸Ģ
    0.10
    èĭ«
    0.10
    åĩºæĿ¥çļĦ
    0.10
    è¿Ļä¹Łæĺ¯
    0.09
    è¿Ļæł·ä¸Ģ
    0.09
    acks
    0.09
    å±ŀäºİèĩªå·±
    0.09
    æĺ¼
    0.09
    Activations Density 0.259%

    No Known Activations