© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29655
    Prev
    Next
    INDEX
    Explanations

    off by, out of, exact match

    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
    Negative Logits
    oms
    -0.09
    éŀŃ
    -0.09
    çľ¨çľ¼
    -0.09
    主ä¹īæĢĿæĥ³
    -0.09
    两边
    -0.09
    èĪ
    -0.08
    åľºéĿ¢
    -0.08
    æ¸
    -0.08
    pository
    -0.08
    ensa
    -0.08
    POSITIVE LOGITS
    exact
    0.11
    ç²¾åĩĨ
    0.11
    åĩĨç¡®
    0.10
    åĪ°ä½į
    0.10
     resemblance
    0.10
    Off
    0.10
    ä¸įåĪ°ä½į
    0.10
    è¦ģ害
    0.09
    精确
    0.09
     exact
    0.09
    Activations Density 0.085%

    No Known Activations