© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 112
    Prev
    Next
    INDEX
    Explanations

    temporal connection before incident

    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
    cheap
    -0.24
    clone
    -0.23
    lower
    -0.23
    æĮ½
    -0.22
     Anth
    -0.22
    æł©
    -0.22
    (acc
    -0.22
     Masters
    -0.21
    ect
    -0.21
    -counter
    -0.21
    POSITIVE LOGITS
     influence
    0.35
    å½±åĵį
    0.31
    åIJįä¹ī
    0.29
    INET
    0.29
    åįıåĬ©
    0.28
     merely
    0.28
    èµŀåĬ©
    0.27
     Influence
    0.27
     influences
    0.25
    æĹłåħ³
    0.25
    Activations Density 0.245%

    No Known Activations