© 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. 11962
    Prev
    Next
    INDEX
    Explanations

    artificial intelligence

    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
    ÑģÑĥжден
    -0.22
    _locator
    -0.21
    ä¸Ģè¾ĪåŃIJ
    -0.21
    ç»ĻåĪ«äºº
    -0.21
    å°Ķæĸ¯
    -0.21
    å°ı康
    -0.20
    éĤ¸
    -0.20
    moz
    -0.20
    ä¸ĢçĶŁ
    -0.19
     spread
    -0.19
    POSITIVE LOGITS
    åĩºè·¯
    0.24
     robotics
    0.20
    alan
    0.20
    人工æĻºèĥ½
    0.20
    åıijå±ķä¸Ń
    0.19
    egt
    0.19
     robotic
    0.18
     Artificial
    0.18
     Sim
    0.18
     Alan
    0.18
    Activations Density 0.020%

    No Known Activations