© 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. 16710
    Prev
    Next
    INDEX
    Explanations

    chain breaker, link, saw, up, promises, email

    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
     tô
    -0.18
    ately
    -0.17
    .GetResponse
    -0.16
    ëĭ¤ê°Ģ
    -0.16
    алÑĮнÑĭй
    -0.16
    jing
    -0.16
     Oval
    -0.16
     sore
    -0.16
    .onCreate
    -0.16
    .annotate
    -0.15
    POSITIVE LOGITS
    纽带
    0.22
    å·¥ä½ľæľºåĪ¶
    0.20
    é¹Ń
    0.20
    æ»ĵ
    0.19
    mates
    0.19
    çĶŁäº§å·¥èīº
    0.19
    èµ·æĿ¥äºĨ
    0.18
    ides
    0.18
    两侧
    0.18
    ä½ıäºĨ
    0.18
    Activations Density 0.015%

    No Known Activations