© 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. 15768
    Prev
    Next
    INDEX
    Explanations

    beneath; underlying; hidden; behind; seems

    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
    å¹²èĦĨ
    -0.21
     Та
    -0.21
    æ£Ģ
    -0.20
    åĬ©æīĭ
    -0.19
    adge
    -0.18
    åģļä¸įåĪ°
    -0.18
    åĢ¬
    -0.18
    opsy
    -0.17
    éħĬ
    -0.17
    è¿Ļç§įäºĭæĥħ
    -0.17
    POSITIVE LOGITS
     hidden
    0.36
     beneath
    0.33
    éļIJèĹı
    0.32
     behind
    0.32
     underlying
    0.32
    hidden
    0.32
    èĥĮåIJİ
    0.32
    èĥĮåIJİçļĦ
    0.30
    èĹıçĿĢ
    0.29
    -hidden
    0.29
    Activations Density 0.043%

    No Known Activations