© 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. 145
    Prev
    Next
    INDEX
    Explanations

    throughout adulthood

    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
    er
    -0.25
    RAY
    -0.21
    ITY
    -0.20
     greatest
    -0.20
    erate
    -0.20
    à¸ĵ
    -0.20
    sing
    -0.20
    ÑĪÑĥ
    -0.19
     tức
    -0.19
    ses
    -0.19
    POSITIVE LOGITS
     throughout
    0.27
    orno
    0.25
    thew
    0.24
    /out
    0.24
    åŃķæľŁ
    0.23
     Throughout
    0.23
    aim
    0.22
    enticate
    0.22
    æĿijåŃIJ
    0.21
     eternity
    0.21
    Activations Density 0.028%

    No Known Activations