© 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. 26657
    Prev
    Next
    INDEX
    Explanations

    atmospheric phenomena and composition

    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
    stä
    -0.10
    æĥij
    -0.09
    讥
    -0.09
    æģ¤
    -0.09
    .Std
    -0.09
    ä¸ļ主
    -0.09
    éĻĮ
    -0.09
    isplay
    -0.09
    âķij
    -0.09
    管åĪ¶
    -0.09
    POSITIVE LOGITS
    å±Ĥ
    0.11
    大æ°Ķ
    0.09
    åı¦ä¸Ģè¾¹
    0.09
    çĶŁäº§æĢ»åĢ¼
    0.09
     atmosphere
    0.09
    ä¸ĩçī©
    0.09
    layer
    0.09
    pheric
    0.08
    è¶Ł
    0.08
    kie
    0.08
    Activations Density 0.029%

    No Known Activations