© 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. 14662
    Prev
    Next
    INDEX
    Explanations

    people on vehicles

    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
    Girl
    -0.21
    .BorderStyle
    -0.21
    errat
    -0.19
    eries
    -0.19
    æµ´
    -0.18
    Girls
    -0.18
    Outdoor
    -0.18
    çĹ£
    -0.18
    å¢Ļ
    -0.18
     bowed
    -0.18
    POSITIVE LOGITS
    ä¹ĺ客
    0.38
     passengers
    0.37
    ä¹ĺåĿIJ
    0.37
    车ä¸Ĭ
    0.37
    车åĨħ
    0.34
    驾驶
    0.33
     onboard
    0.32
    驾驶åijĺ
    0.32
     passenger
    0.31
    车åİ¢
    0.30
    Activations Density 0.119%

    No Known Activations