© 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. 56716
    Prev
    Next
    INDEX
    Explanations

    beaches and coastlines

    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
    æ»ĭ
    -0.12
    åĤ¬
    -0.09
    ucci
    -0.09
    ç«Ļåľ¨
    -0.09
    ison
    -0.08
    ä¸Ģ件
    -0.08
    æ»ĭçĶŁ
    -0.08
    å¨ģ
    -0.08
    éģĩ
    -0.08
    rack
    -0.08
    POSITIVE LOGITS
     beaches
    0.16
    海滩
    0.14
     beach
    0.12
    æ²Ļ滩
    0.12
    æµ·æ¹¾
    0.10
    æĿ¿
    0.10
    _locs
    0.10
    åĬ¨éĿĻ
    0.09
     Beach
    0.09
    天åłĤ
    0.09
    Activations Density 0.119%

    No Known Activations