© 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. 11876
    Prev
    Next
    INDEX
    Explanations

    occupants in vehicles or 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
    èłķ
    -0.22
    èį«
    -0.20
    éĺ´
    -0.20
    弦
    -0.20
     thirsty
    -0.20
    çĸı
    -0.19
    lette
    -0.19
     Cats
    -0.19
    çħ®
    -0.19
    æ°´æºIJ
    -0.18
    POSITIVE LOGITS
    伤亡
    0.28
    æijĶåĢĴ
    0.27
     crash
    0.26
    车åĨħ
    0.25
    éĩį伤
    0.25
    车ä¸Ĭ
    0.24
    车祸
    0.24
    -seat
    0.24
    头éĥ¨
    0.24
    交éĢļäºĭæķħ
    0.24
    Activations Density 0.053%

    No Known Activations