© 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. 16133
    Prev
    Next
    INDEX
    Explanations

    mathematics and finance concepts

    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
    åīįä»»
    -0.26
    /documentation
    -0.21
    ugg
    -0.20
    .semantic
    -0.20
    仡
    -0.19
    以å¾Ģ
    -0.19
    ouv
    -0.19
     Manuals
    -0.19
    ikal
    -0.18
    æģIJ
    -0.18
    POSITIVE LOGITS
     basics
    0.34
     concepts
    0.28
    å¤įä¹ł
    0.28
    çļĦåŁºæľ¬
    0.27
     basic
    0.26
    åľ¨çĶŁæ´»ä¸Ń
    0.26
    çļĦæ¦Ĥ念
    0.25
     topics
    0.24
     Quiz
    0.24
    åŁºæľ¬
    0.24
    Activations Density 0.101%

    No Known Activations