© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8566
    Prev
    Next
    INDEX
    Explanations

    satellite observation

    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
     Peaks
    -0.09
    æİ¥ç§į
    -0.09
    æĪĺæľ¯
    -0.09
    ê°ģ
    -0.09
    _allocated
    -0.08
    .uc
    -0.08
    交éĢļå®īåħ¨
    -0.08
    å¯Į
    -0.08
    çĤ¹æ»´
    -0.08
    顺
    -0.08
    POSITIVE LOGITS
    åį«æĺŁ
    0.12
    sat
    0.12
     satellite
    0.11
     sat
    0.11
     satellites
    0.10
    éģ¥
    0.10
    .sat
    0.10
    _sat
    0.10
     Sat
    0.10
    Sat
    0.10
    Activations Density 0.054%

    No Known Activations