© 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. 10861
    Prev
    Next
    INDEX
    Explanations

    progress and status updates

    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
    ä¸įä¸ĭ
    -0.20
    -exclusive
    -0.20
    èĥ½å¤Łè®©
    -0.20
    å·³
    -0.20
    ä¸Ģçľĭ
    -0.20
    以为
    -0.19
    丰æĶ¶
    -0.19
    éħ¸
    -0.19
    èĩ»
    -0.18
    欲
    -0.18
    POSITIVE LOGITS
     progress
    0.23
    éĻĨç»Ń
    0.23
    progress
    0.22
    -progress
    0.22
    è¿ĽæŃ¥
    0.21
    ikes
    0.20
    Progress
    0.20
     Progress
    0.20
    è¿ĽæĿ¥
    0.19
     اÙĦÙĪاØŃد
    0.18
    Activations Density 0.037%

    No Known Activations