© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12230
    Prev
    Next
    INDEX
    Explanations

    punctuation and symbols

    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
     "
    -0.21
     AFL
    -0.18
    æ½®
    -0.18
    è¿Ń
    -0.17
     pass
    -0.17
    teil
    -0.16
    Christopher
    -0.16
    adar
    -0.16
     estate
    -0.16
    _cu
    -0.16
    POSITIVE LOGITS
    uvre
    0.20
    çłľ
    0.18
    å¹´ä¹ĭä¹ħ
    0.18
    æĺ¯åĽ½åĨħ
    0.18
    nbsp
    0.17
    èī®
    0.17
    ä¸Ģä¸Ŀ
    0.17
    ç³Ł
    0.17
    Backing
    0.17
    åī¥
    0.17
    Activations Density 0.155%

    No Known Activations