© 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. 56111
    Prev
    Next
    INDEX
    Explanations

    American

    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
    å½ĵä¸ĭ
    -0.10
    MouseDown
    -0.10
    æĽ´ä½ķåĨµ
    -0.10
    æijĨæĶ¾
    -0.09
    åı¤ä»Ĭ
    -0.09
    ÑİÑģÑĮ
    -0.09
    èģ¿
    -0.09
     вз
    -0.09
    éĩĬ
    -0.09
    缴è¨Ģ
    -0.09
    POSITIVE LOGITS
    ucha
    0.08
    ä¸įæĪIJ
    0.08
     lan
    0.08
    èIJ½åIJİ
    0.08
    æı®
    0.08
    Assistant
    0.08
    nage
    0.07
    ugg
    0.07
     pronounce
    0.07
    _lite
    0.07
    Activations Density 0.004%

    No Known Activations