© 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. 54847
    Prev
    Next
    INDEX
    Explanations

    water bodies and locations

    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
    åĩłå¼ł
    -0.10
    ãģ¡ãĤĩ
    -0.09
    .Up
    -0.09
    à¸Ńà¸Ļ
    -0.09
    adin
    -0.09
    èĪĮå°ĸ
    -0.09
    little
    -0.09
    heed
    -0.09
    å®Į
    -0.08
    ÑģÑĤавлен
    -0.08
    POSITIVE LOGITS
    è¾¹
    0.09
    ä¹ĭå¿ĥ
    0.09
    åı¦ä¸Ģè¾¹
    0.09
    éĤ£è¾¹
    0.09
    side
    0.08
    bnb
    0.08
    滨
    0.08
    ä»İæĿ¥æ²¡
    0.08
    æĮ¨
    0.08
    é£İåħī
    0.08
    Activations Density 0.041%

    No Known Activations