© 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. 33530
    Prev
    Next
    INDEX
    Explanations

    dates and specific events

    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
    主è¦ģä»İäºĭ
    -0.10
    åIJİæĤĶ
    -0.10
    以åIJİ
    -0.10
    ä»ĬåIJİ
    -0.10
    ais
    -0.09
    å½ĵåľº
    -0.09
    主èIJ¥ä¸ļåĬ¡
    -0.09
    enge
    -0.09
    第ä¸ĢèĬĤ
    -0.09
    ä¸ĭ次
    -0.09
    POSITIVE LOGITS
    æıIJåīį
    0.16
     prepar
    0.16
    åĩĨå¤ĩ
    0.15
     подгоÑĤов
    0.14
    åħĪè¡Į
    0.14
    é¢Ħå¤ĩ
    0.14
    åĩĨå¤ĩå·¥ä½ľ
    0.14
    çŃ¹å¤ĩ
    0.14
    Preparing
    0.13
     preparation
    0.13
    Activations Density 0.174%

    No Known Activations