© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37932
    Prev
    Next
    INDEX
    Explanations

    leisure time activities

    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
    顺åĬ¿
    -0.10
    饿
    -0.09
    afil
    -0.09
    åѤç«ĭ
    -0.09
    zig
    -0.09
    áŀł
    -0.09
    upa
    -0.09
    éģĹæ¼ı
    -0.08
    _EMPTY
    -0.08
    iani
    -0.08
    POSITIVE LOGITS
    ä¸įæĪIJ
    0.09
    æ¡ĥ
    0.09
    iaux
    0.08
    æĺ¥ç§ĭ
    0.08
    宫
    0.08
    设æĸ½å»ºè®¾
    0.08
    æįı
    0.08
    åĬłçĽŁåºĹ
    0.08
    _fac
    0.08
    è¿ĩ度
    0.08
    Activations Density 0.012%

    No Known Activations