© 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. 53469
    Prev
    Next
    INDEX
    Explanations

    code comments or separators

    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
    议论
    -0.09
    enty
    -0.08
    èī¯å¿ĥ
    -0.08
    ä¸įçĶĺ
    -0.08
     Protest
    -0.08
    TabPage
    -0.08
    ç»ıåİĨ
    -0.08
    æĩĴ
    -0.08
    åİĨæŶ
    -0.08
    æ·±æ·±åľ°
    -0.08
    POSITIVE LOGITS
    åıijå±ķæĪĺçķ¥
    0.10
    大å®ĹåķĨåĵģ
    0.10
    ä¹ĭéģĵ
    0.09
    ç§ijæĬĢèĤ¡ä»½
    0.09
    äºĴè¡¥
    0.09
    Ñįкон
    0.09
    .Matcher
    0.09
    å¤§èµĽ
    0.09
    ÙħÙĬÙĦ
    0.09
    è¿Ļä¸Ģå¹´
    0.09
    Activations Density 0.038%

    No Known Activations