© 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. 50055
    Prev
    Next
    INDEX
    Explanations

    top, bottom, left

    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
    èĩ³äºİ
    -0.11
    ä¸ĬéŨ
    -0.09
    åĬłæ·±
    -0.09
     зай
    -0.09
    ë§ģ
    -0.08
    -ajax
    -0.08
    åľ¨å®¶
    -0.08
    dit
    -0.08
    æ³®
    -0.08
    eyed
    -0.08
    POSITIVE LOGITS
    常åĬ¡åī¯
    0.10
    éĻIJ度
    0.09
    /on
    0.09
    ASTER
    0.09
    人人éĥ½
    0.09
    æīĵäºĨ
    0.09
     него
    0.09
    主æĮģ
    0.09
    å¼ĢèĬ±
    0.09
    çļİ
    0.08
    Activations Density 0.070%

    No Known Activations