© 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. 13561
    Prev
    Next
    INDEX
    Explanations

    finishing or completion

    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
    èĻ¬
    -0.19
    å¢ī
    -0.19
    steen
    -0.19
    åŁºåĩĨ
    -0.18
    çĻ¸
    -0.18
    ante
    -0.18
    -Co
    -0.17
    ersion
    -0.17
    avar
    -0.17
    å¢ŀåĢ¼æľįåĬ¡
    -0.17
    POSITIVE LOGITS
    åī©ä¸ĭçļĦ
    0.23
    åı¦ä¸ĢåįĬ
    0.23
    åģļå®Į
    0.23
     unfinished
    0.22
    unfinished
    0.22
    å®ĮåĸĦ
    0.22
    åĴĮå®ĮåĸĦ
    0.21
     completion
    0.21
    åī©ä¸ĭ
    0.21
    Incomplete
    0.20
    Activations Density 0.024%

    No Known Activations