© 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. 909
    Prev
    Next
    INDEX
    Explanations

    Socrates, Plato, Greek philosophy

    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
    æŁ¥çľĭåħ¨æĸĩ
    -0.26
    æĬł
    -0.25
     mascara
    -0.25
    è¾°
    -0.23
    æŀĹä¸ļ
    -0.23
    éĤ®æĶ¿
    -0.23
     Shooter
    -0.22
     redundancy
    -0.22
     mer
    -0.22
     telemetry
    -0.22
    POSITIVE LOGITS
     Athens
    0.38
     Plato
    0.38
     Athen
    0.33
    Greek
    0.30
     Greek
    0.30
     Greeks
    0.29
    å¸ĮèħĬ
    0.28
    对è¯Ŀ
    0.27
     Greece
    0.26
    EIF
    0.26
    Activations Density 0.012%

    No Known Activations