© 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. 27088
    Prev
    Next
    INDEX
    Explanations

    travel and places

    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
    loo
    -0.09
    tical
    -0.09
    主ä½ĵ
    -0.09
    éĢµ
    -0.08
    æı´
    -0.08
    èķĬ
    -0.08
    ä¾ĭå¤ĸ
    -0.08
    developers
    -0.08
    ervo
    -0.08
    iks
    -0.08
    POSITIVE LOGITS
    è°
    0.11
    ä¸įåIJĮçļĦ
    0.11
    足迹
    0.10
     пÑĢежде
    0.10
    è°ĥçłĶ
    0.10
    å¸Ĥåİ¿
    0.09
    åIJĦåľ°
    0.09
    {{{
    0.09
     khắp
    0.09
    éģį
    0.09
    Activations Density 0.054%

    No Known Activations