© 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. 12026
    Prev
    Next
    INDEX
    Explanations

    cars and dealerships

    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
    packed
    -0.20
    æĺ¥æĻļ
    -0.19
    çľĩ
    -0.19
    èĤļåŃIJ
    -0.19
    ðŁİ¨
    -0.19
     flute
    -0.18
    ulers
    -0.18
     cep
    -0.18
    food
    -0.18
     cooker
    -0.18
    POSITIVE LOGITS
    æĸ°è½¦
    0.35
    è´Ń车
    0.30
    车åŀĭ
    0.29
    äºĮæīĭ车
    0.28
    åĨħ饰
    0.27
    è¡Į驶
    0.27
    车è¾Ĩ
    0.26
     driv
    0.25
    驾驶
    0.25
     dealership
    0.24
    Activations Density 0.065%

    No Known Activations