© 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. 52958
    Prev
    Next
    INDEX
    Explanations

    copy, modify, distribute, or broadcast

    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¯Ļ
    -0.11
    æĦŁåħ´è¶£çļĦ
    -0.10
    iger
    -0.09
    gere
    -0.09
    éĤ£ä¸ªæŶåĢĻ
    -0.08
    igin
    -0.08
    æĸĩåĮĸ建设
    -0.08
    è¾ĺ
    -0.08
    客è§Ĥ
    -0.08
    ä»ĭ
    -0.08
    POSITIVE LOGITS
    å¤įåĪ¶
    0.09
    åĢĴ
    0.09
    èĢĥæŁ¥
    0.09
    .xlim
    0.08
    quo
    0.08
    åŃº
    0.08
    太快
    0.08
     неÑģк
    0.08
    _reverse
    0.08
    acom
    0.08
    Activations Density 0.014%

    No Known Activations