© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10403
    Prev
    Next
    INDEX
    Explanations

    rental cars and hire

    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
    Negative Logits
    Content
    -0.21
     content
    -0.21
    owie
    -0.21
    ä½Ĺ
    -0.20
    SETTINGS
    -0.19
     Content
    -0.19
    ERIC
    -0.19
    _content
    -0.19
    èĨı
    -0.19
    æĢ§å¼º
    -0.19
    POSITIVE LOGITS
    ç§Łè½¦
    0.26
    èĩªé©¾
    0.24
    驶
    0.22
    åĽ½éĻħ
    0.22
    åı¸æľº
    0.22
    è¡Į驶
    0.22
    秣èµģ
    0.22
    å¢ĥåĨħ
    0.20
     cars
    0.20
    秣
    0.20
    Activations Density 0.006%

    No Known Activations