© 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. 14623
    Prev
    Next
    INDEX
    Explanations

    aspirations and future careers

    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
    ä¾ĽéľĢ
    -0.28
    éľĢæ±Ĥ
    -0.20
    .lastIndexOf
    -0.20
    alink
    -0.20
    èĥľè´Ł
    -0.19
    isks
    -0.19
    ahl
    -0.19
    chers
    -0.19
     localVar
    -0.18
    ä¸ĵ家ç»Ħ
    -0.18
    POSITIVE LOGITS
     someday
    0.35
    æĪIJ为ä¸ĢåIJį
    0.26
    åĪ°æŶåĢĻ
    0.26
     eventually
    0.25
    å°ĨæĿ¥
    0.25
     бÑĥд
    0.23
    å±ĬæŶ
    0.22
    æľīä¸Ģ天
    0.22
    缮åīįæŃ£åľ¨
    0.22
     eventual
    0.21
    Activations Density 0.023%

    No Known Activations