© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15140
    Prev
    Next
    INDEX
    Explanations

    educational attainment

    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
    çŃĶçĸij
    -0.20
    VIP
    -0.20
    @email
    -0.19
    管è¾ĸ
    -0.19
     lipstick
    -0.19
     ByVal
    -0.18
    æĥ¬
    -0.18
    éĢıæĺİ
    -0.18
    linger
    -0.18
    ç´«å¤ĸ
    -0.18
    POSITIVE LOGITS
     wage
    0.23
    åѦåİĨ
    0.23
    è¾į
    0.21
    工人
    0.21
    utex
    0.21
    dek
    0.20
    oop
    0.20
    ANI
    0.19
     sá»ijng
    0.19
    jah
    0.19
    Activations Density 0.019%

    No Known Activations