© 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. 11153
    Prev
    Next
    INDEX
    Explanations

    quantum cryptography, computer chips, display devices

    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
    @Module
    -0.22
    ä¸īæĸ¹
    -0.21
    assel
    -0.20
    人为
    -0.20
    olson
    -0.19
     UIF
    -0.18
    ESIS
    -0.18
     rims
    -0.18
    Expose
    -0.18
    ober
    -0.18
    POSITIVE LOGITS
    éĩıåŃIJ
    0.33
     quantum
    0.28
    èĬ¯çīĩ
    0.26
    å¤ĦçIJĨåĻ¨
    0.26
    æĻ¶ä½ĵ
    0.24
    çĶµè·¯
    0.24
    åĻ¨ä»¶
    0.24
    çĶµèĦij
    0.23
     processors
    0.22
    æ··æ²Į
    0.22
    Activations Density 0.145%

    No Known Activations