© 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. 471
    Prev
    Next
    INDEX
    Explanations

    traffic safety violations

    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
    å·¥ä½ľæĸ¹æ¡Ī
    -0.26
     Ribbon
    -0.24
     crist
    -0.24
    èħ¥
    -0.24
     ferment
    -0.23
     planned
    -0.23
     Protestant
    -0.23
    åıijå±ķæ½ľåĬĽ
    -0.23
    æºIJæºIJ
    -0.23
    plans
    -0.23
    POSITIVE LOGITS
    交èѦ
    0.40
    è¿Ŀç«ł
    0.39
    æľºåĬ¨è½¦
    0.36
     violations
    0.35
    驾驶
    0.34
    å¤Ħç½ļ
    0.34
    åģľè½¦
    0.33
     motorists
    0.32
    è·¯åĨµ
    0.31
    è§ĦèĮĥ
    0.31
    Activations Density 0.011%

    No Known Activations