© 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. 1097
    Prev
    Next
    INDEX
    Explanations

    first before noun

    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
    ä¸įæĸŃå¢ŀåĬł
    -0.09
    è´´åIJ§
    -0.09
    ç½ij绾å®īåħ¨
    -0.09
    ARGV
    -0.09
     CURL
    -0.09
    æĸ¯åŁº
    -0.09
    ä¼Ĺ
    -0.09
    åľ¨ä¸ŃåĽ½
    -0.09
    æĵį
    -0.08
    ulerAngles
    -0.08
    POSITIVE LOGITS
    rou
    0.10
    è§ģåĪ°
    0.09
     ÑįÑĤап
    0.09
    æ¯ķç«Łæĺ¯
    0.09
    iw
    0.09
     stages
    0.09
    éĺ¶æ®µæĢ§
    0.09
    éĺ¶æ®µ
    0.08
    iom
    0.08
    äºĮèĢħ
    0.08
    Activations Density 0.086%

    No Known Activations