© 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. 35458
    Prev
    Next
    INDEX
    Explanations

    vibrant and active places

    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
    çĶŁçī©åѦ
    -0.09
    åĿIJä¸ĭ
    -0.09
    å²IJ
    -0.09
    èĵĿ天
    -0.09
    è§īæĤŁ
    -0.09
    ç²¾åĵģ
    -0.09
    èĬĤ缮ä¸Ń
    -0.09
    enser
    -0.09
    viewer
    -0.09
    带éĺŁ
    -0.09
    POSITIVE LOGITS
    çĥŃéĹ¹
    0.16
    æ´»åĬĽ
    0.14
    çĶŁæľº
    0.14
     bustling
    0.14
    人æ°Ķ
    0.13
     vibrant
    0.13
    å¿Ļç¢Į
    0.12
    ç¹ģèį£
    0.12
    çĨĻ
    0.12
    åĺĪ
    0.12
    Activations Density 0.189%

    No Known Activations