© 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. 11813
    Prev
    Next
    INDEX
    Explanations

    refuses, king, thrown, choose

    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
    çĥ¦
    -0.23
    说ä¸įåĩº
    -0.21
    çĽĬ
    -0.20
    åĪ¶
    -0.20
    ages
    -0.19
     BOOST
    -0.18
    Forward
    -0.18
    ç©¿è¡£
    -0.18
    ä¸įå°ıçļĦ
    -0.18
    ([]*
    -0.18
    POSITIVE LOGITS
    忽çķ¥
    0.23
    忽çķ¥äºĨ
    0.21
    æĭĴç»Ŀ
    0.21
    以人为
    0.21
    ocale
    0.20
     Earn
    0.20
    饲åħ»
    0.20
    éĢīæĭ©äºĨ
    0.19
    æī§æĦı
    0.19
    cka
    0.19
    Activations Density 0.051%

    No Known Activations