© 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. 17735
    Prev
    Next
    INDEX
    Explanations

    shallow water or depth

    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
    ç«ŀæĬĢ
    -0.09
    æģ¯
    -0.09
    ãĥ¬ãĤ¹
    -0.09
    飬
    -0.09
    åı¦è¡Į
    -0.09
    åħ¬ç§¯éĩij
    -0.09
    两级
    -0.08
    æ±īåł¡
    -0.08
    ä¿Ŀå®ī
    -0.08
    åĭ
    -0.08
    POSITIVE LOGITS
    æµħ
    0.12
    河水
    0.12
    淹没
    0.11
     shallow
    0.11
    深度
    0.11
    _depth
    0.10
    æ·º
    0.10
    depth
    0.10
     depth
    0.10
    dit
    0.10
    Activations Density 0.047%

    No Known Activations