© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 537
    Prev
    Next
    INDEX
    Explanations

    space, astronomy, planets, NASA

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    篾
    -0.27
     laundering
    -0.24
    å®ŀæľ¨
    -0.24
    Mex
    -0.24
    íĮ¨
    -0.23
     launder
    -0.23
     Dominican
    -0.23
    Resistance
    -0.23
    éħ©
    -0.22
    ottage
    -0.22
    POSITIVE LOGITS
    太空
    0.73
    å®ĩå®Ļ
    0.63
     NASA
    0.62
    è¡ĮæĺŁ
    0.61
    NASA
    0.61
    天æĸĩ
    0.61
    èĪªå¤©
    0.59
     astronomy
    0.57
    åľ°çIJĥ
    0.57
    æĺŁéĻħ
    0.57
    Activations Density 0.198%

    No Known Activations