© 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. 12184
    Prev
    Next
    INDEX
    Explanations

    traffic safety and accidents

    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
    .clients
    -0.21
    gree
    -0.20
    ä¸ĭåİ»
    -0.20
    精油
    -0.20
    ILED
    -0.20
    _TEMP
    -0.20
    AZY
    -0.19
    èĬĭ
    -0.19
     Temporary
    -0.19
    _growth
    -0.18
    POSITIVE LOGITS
    çļĦå®īåħ¨
    0.29
    å®īåħ¨æĢ§
    0.29
    å®īåħ¨
    0.29
     safety
    0.27
    æĬĹéľĩ
    0.25
    éĺ²åį«
    0.25
    éĺ²æĬ¤
    0.25
    ä¿ĿæĬ¤
    0.25
    Safety
    0.24
    è¯Ħ级
    0.24
    Activations Density 0.008%

    No Known Activations