© 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. 514
    Prev
    Next
    INDEX
    Explanations

    winning percentage

    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
    æī©å®¹
    -0.29
     Tonight
    -0.25
    åIJĪå½±
    -0.24
     Shelby
    -0.24
    jie
    -0.23
    åıªåī©ä¸ĭ
    -0.23
    dsa
    -0.22
     malfunction
    -0.22
     renewed
    -0.22
    åģľçĶµ
    -0.22
    POSITIVE LOGITS
     average
    0.41
     averaged
    0.41
     averages
    0.41
     avg
    0.40
    å¹³åĿĩæ°´å¹³
    0.39
    å¹³åĿĩ
    0.38
    -average
    0.36
     Average
    0.36
    .avg
    0.35
    Average
    0.34
    Activations Density 0.006%

    No Known Activations