© 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. 15423
    Prev
    Next
    INDEX
    Explanations

    early childhood education

    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
    çıŃéķ¿
    -0.21
    à¸Ļà¸Ńà¸ģ
    -0.21
    redi
    -0.19
    ucer
    -0.19
    åIJįæł¡
    -0.19
    MED
    -0.18
    åīĬ
    -0.18
    clone
    -0.18
    å´Ģ
    -0.18
    å®ıè§Ĥç»ıæµİ
    -0.18
    POSITIVE LOGITS
    åĴ¿
    0.23
    æķĻèĤ²
    0.23
     education
    0.23
    education
    0.21
    ervices
    0.20
    ä¸Ģä½ĵåĮĸ
    0.19
    incare
    0.19
    ounter
    0.19
    croft
    0.19
    ä¸Ģ代
    0.18
    Activations Density 0.021%

    No Known Activations