© 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. 5874
    Prev
    Next
    INDEX
    Explanations

    nmap .org, cities, King, android

    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
    èĹ»
    -0.10
    çļĦæĪIJéķ¿
    -0.09
    åľ¹
    -0.09
    ä¸Ŀè·¯
    -0.09
     recur
    -0.09
    .ga
    -0.09
    ä¸IJ
    -0.09
    å¾Īæ·±
    -0.09
     giản
    -0.09
    èĴ
    -0.09
    POSITIVE LOGITS
     Trojan
    0.09
    .Scan
    0.09
    æİ¢æµĭ
    0.09
    æİ¢
    0.09
    æĺİæĺİ
    0.08
    åĪ°è¾¾
    0.08
    _weak
    0.08
     owes
    0.08
    Scanner
    0.08
     prospect
    0.08
    Activations Density 0.058%

    No Known Activations