© 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. 39565
    Prev
    Next
    INDEX
    Explanations

    geographic entities and related media

    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
    享èªī
    -0.09
    GY
    -0.09
    åįļä¼ļ
    -0.08
    ä¸ķ
    -0.08
    é©¿
    -0.08
    åIJī
    -0.08
    å¤ĸæı´
    -0.08
    .Transparent
    -0.08
    tails
    -0.08
    æĢĶ
    -0.07
    POSITIVE LOGITS
    éĻIJ度
    0.10
    尺度
    0.10
    羣åģĩ
    0.10
    ardin
    0.10
    raw
    0.09
    çĸ¡
    0.09
    ä½Ĩä¸įéĻIJ
    0.09
    笥
    0.09
    conda
    0.09
    chia
    0.09
    Activations Density 0.003%

    No Known Activations