© 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. 6393
    Prev
    Next
    INDEX
    Explanations

    ability to

    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
    ä¹ħäºĨ
    -0.10
    è¯ļæĦı
    -0.09
    äºī夺
    -0.09
    otty
    -0.09
    ergy
    -0.09
    éļ¾åħį
    -0.09
    åħ¬æ°ij
    -0.08
     поÑģл
    -0.08
    ibia
    -0.08
    èĴ¸
    -0.08
    POSITIVE LOGITS
    平衡
    0.11
    æ´ŀå¯Ł
    0.10
    åıijçİ°èĩªå·±
    0.10
     compartment
    0.09
    æĬ¼
    0.09
    çľĭåĩº
    0.08
    ä¸į失
    0.08
    ä¼ļåIJĮ
    0.08
    éĻ·
    0.08
     balance
    0.08
    Activations Density 0.042%

    No Known Activations