© 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. 58084
    Prev
    Next
    INDEX
    Explanations

    Plaza and Vista locations

    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
    zelf
    -0.11
    设æĸ½å»ºè®¾
    -0.10
    eren
    -0.10
    侬
    -0.10
    ä½İåİĭ
    -0.09
     khÄĥn
    -0.09
    eel
    -0.09
    smith
    -0.09
    ä¸įèĪį
    -0.09
    ulus
    -0.09
    POSITIVE LOGITS
    åįĥåı¤
    0.09
    chet
    0.09
    ../../../
    0.09
     incom
    0.08
    andro
    0.08
    à¤Ŀ
    0.08
    olars
    0.08
    OLA
    0.08
    že
    0.08
     ÑĤоÑĩно
    0.08
    Activations Density 0.005%

    No Known Activations