© 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. 1379
    Prev
    Next
    INDEX
    Explanations

    amounts of money

    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
    asty
    -0.25
    å¾ĹåĪĨ
    -0.24
    Trace
    -0.22
    æİ£
    -0.21
     dwelling
    -0.21
    å¼
    -0.21
    秽
    -0.21
     ChÃŃ
    -0.21
    forge
    -0.21
    Compatible
    -0.21
    POSITIVE LOGITS
    å·¦åı³
    0.31
    以ä¸ĬçļĦ
    0.26
     spreads
    0.25
     Pins
    0.22
    æľºæ¢°è®¾å¤ĩ
    0.22
    æµĵ
    0.22
    åīįåIJİ
    0.22
    rypt
    0.21
    (!
    0.21
     Brush
    0.21
    Activations Density 0.020%

    No Known Activations