© 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. 13794
    Prev
    Next
    INDEX
    Explanations

    vehicle equipment and automotive industries

    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
    robe
    -0.22
    ulers
    -0.20
    çģ¯ç¬¼
    -0.20
    irty
    -0.20
    .weixin
    -0.18
    åĽ¢
    -0.18
    åĮĹ大
    -0.18
    绿è±Ĩ
    -0.18
    çģ«çĤ¬
    -0.18
    ä¸Ńæĸ°
    -0.18
    POSITIVE LOGITS
    汽车
    0.44
    车è¾Ĩ
    0.38
     vehicle
    0.38
     cars
    0.36
    æ±½è»Ĭ
    0.34
    车
    0.33
    æķ´è½¦
    0.33
    è¡Į驶
    0.32
    æľºåĬ¨è½¦
    0.32
     авÑĤомобилÑı
    0.31
    Activations Density 0.355%

    No Known Activations