© 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. 939
    Prev
    Next
    INDEX
    Explanations

    historical events and remembrance

    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
    çĶ·æĸ¹
    -0.24
    èĨ³
    -0.24
     consort
    -0.24
    éĢĹ
    -0.23
    åħĪ导
    -0.23
    å°ıå·§
    -0.23
    çľĭ好
    -0.23
    åĬŀäºĭ
    -0.23
    uide
    -0.23
     Arist
    -0.23
    POSITIVE LOGITS
    åİĨåı²
    0.51
     historical
    0.49
    纪念
    0.47
    çļĦåİĨåı²
    0.47
     commemor
    0.47
    éĵŃè®°
    0.46
     history
    0.46
     memories
    0.44
    æŃ·åı²
    0.44
     commem
    0.43
    Activations Density 0.153%

    No Known Activations