© 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. 12912
    Prev
    Next
    INDEX
    Explanations

    computer and networks

    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
    .getChannel
    -0.23
     hus
    -0.20
    çĸı
    -0.20
    æ²½
    -0.20
    ksen
    -0.20
    maids
    -0.20
    Sdk
    -0.19
     hã
    -0.18
    аÑĤег
    -0.18
     channel
    -0.18
    POSITIVE LOGITS
    çĶµèĦij
    0.45
     computer
    0.41
     computers
    0.41
    计ç®Ĺæľº
    0.40
     ì»´íĵ¨íĦ°
    0.35
     компÑĮÑİÑĤеÑĢ
    0.35
    鼻èħ¦
    0.34
    computer
    0.33
    æ¡ĮéĿ¢
    0.30
     Computers
    0.29
    Activations Density 0.139%

    No Known Activations