© 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. 12984
    Prev
    Next
    INDEX
    Explanations

    cryptocurrency and blockchain

    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
    æļijæľŁ
    -0.23
    çĶ¨åĵģ
    -0.21
    Miss
    -0.21
     ев
    -0.21
    æĶ¾æīĭ
    -0.21
    åįģäºĮäºĶ
    -0.20
    æĥħåķĨ
    -0.20
    å¸ĥç½®
    -0.20
    æļij
    -0.19
    AAF
    -0.19
    POSITIVE LOGITS
    交æĺĵ
    0.35
     transactions
    0.28
     blockchain
    0.28
    交æĺĵå¹³åı°
    0.27
    æ¯Ķçī¹å¸ģ
    0.26
     transaction
    0.26
    åĮºåĿĹéĵ¾
    0.26
    æīĭç»Ńè´¹
    0.25
    .Bit
    0.25
     Ethereum
    0.24
    Activations Density 0.140%

    No Known Activations