© 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. 61667
    Prev
    Next
    INDEX
    Explanations

    botany and entomology

    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
    éĽĩ
    -0.09
    é¦ĭ
    -0.09
    rei
    -0.09
    产ä¸ļéĵ¾
    -0.08
    åĵij
    -0.08
    æī«
    -0.08
    APA
    -0.08
    strand
    -0.08
    æĭĴç»Ŀ
    -0.08
    åĭĩ
    -0.08
    POSITIVE LOGITS
    èĬ±åįī
    0.10
    lein
    0.10
    纲
    0.09
    æĭįæĭį
    0.09
    erial
    0.09
    è¿ľæĻ¯
    0.09
    çķĮçļĦ
    0.09
    æ¯ĶæĭŁ
    0.09
    ensive
    0.09
    æ¯ĶåĪĨ
    0.09
    Activations Density 0.243%

    No Known Activations