© 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. 16837
    Prev
    Next
    INDEX
    Explanations

    supporters or proponents

    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
    icity
    -0.23
    cape
    -0.21
    éĥ¨åĪĨåĨħ容
    -0.19
    åĴİ
    -0.18
    urally
    -0.18
    æĪŁ
    -0.17
     Ñģобой
    -0.17
     اÙĦدÙĨÙĬا
    -0.16
    apult
    -0.16
    ural
    -0.16
    POSITIVE LOGITS
    们
    0.23
    hood
    0.21
    ниÑĨа
    0.20
    hip
    0.20
    们çļĦ
    0.18
     mãi
    0.18
    lla
    0.18
    é¢Ĩè¢ĸ
    0.17
    ethod
    0.17
    /commons
    0.17
    Activations Density 0.013%

    No Known Activations