© 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. 13482
    Prev
    Next
    INDEX
    Explanations

    car brands and models

    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
    èĵĸ
    -0.20
    emer
    -0.20
    æĩĴ
    -0.19
    .Cells
    -0.19
     Rao
    -0.19
     Certain
    -0.18
    _INPUT
    -0.18
    ç¼¢
    -0.18
    kker
    -0.18
    åİ»åĵªåĦ¿
    -0.18
    POSITIVE LOGITS
    åıĤèµĽ
    0.24
    åİŁåŀĭ
    0.23
    릿
    0.23
    夺åĨł
    0.22
    æĶ¹éĢł
    0.20
    åħĪè¡Į
    0.20
    çĶ±ä¸ŃåĽ½
    0.20
     prototype
    0.19
     Prototype
    0.19
    ÑĢеÑĪ
    0.19
    Activations Density 0.017%

    No Known Activations