© 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. 18303
    Prev
    Next
    INDEX
    Explanations

    led to

    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
    elter
    -0.09
     знаÑĤÑĮ
    -0.08
    è¿ķ
    -0.08
    é³ĥ
    -0.08
     Vie
    -0.08
    åįķä½į
    -0.08
    íħį
    -0.08
    è¿Ļæł·ä¸ĢæĿ¥
    -0.08
     chc
    -0.08
    ldata
    -0.07
    POSITIVE LOGITS
    æİĸ
    0.11
    人们对
    0.10
    ended
    0.09
    emann
    0.09
    Accepted
    0.09
    -ons
    0.09
    æľī人说
    0.09
    人们
    0.09
    ä¸įäºĨ
    0.09
    ä¸ĸ人
    0.08
    Activations Density 0.023%

    No Known Activations