© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 13743
    Prev
    Next
    INDEX
    Explanations

    pedestrian safety and traffic controls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    æ°´è´¨
    -0.24
    åı£åij³
    -0.23
    楼主
    -0.23
    ansi
    -0.21
    -css
    -0.20
    æĪĴ
    -0.20
    éļĶå£ģ
    -0.19
    éĺģ
    -0.19
    èµĦè´¨
    -0.19
    hai
    -0.19
    POSITIVE LOGITS
    è¡Į人
    0.29
     safer
    0.25
    交éĢļå®īåħ¨
    0.24
    danger
    0.24
    unsafe
    0.24
     dangers
    0.23
     danger
    0.22
    ä¿ĿæĬ¤åĮº
    0.22
    åį±éĻ©
    0.22
    Danger
    0.21
    Activations Density 0.021%

    No Known Activations