© 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. 18956
    Prev
    Next
    INDEX
    Explanations

    in [preposition indicating location, time, or category]

    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
    ahi
    -0.09
    aina
    -0.09
    人ãģ¨
    -0.09
    èģĶç³»æĪij们
    -0.09
    .nt
    -0.09
    _nt
    -0.09
    nt
    -0.08
     Lives
    -0.08
    ound
    -0.08
    aires
    -0.08
    POSITIVE LOGITS
    æľĪä¸ĭ
    0.09
    æĵĺ
    0.09
    ä¸ĢåIJĮ
    0.08
    è¨Ģè¡Į
    0.08
    åħ¨äº§ä¸ļéĵ¾
    0.08
    åijµæĬ¤
    0.08
    èĮ¬
    0.08
    æĥ¯
    0.08
    åľ¨å¸Ĥåľºä¸Ĭ
    0.08
    éĥ½è®¤ä¸º
    0.08
    Activations Density 0.130%

    No Known Activations