© 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. 15708
    Prev
    Next
    INDEX
    Explanations

    charters, alkoxylates, enrichment, fenders, gator

    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
    .datatables
    -0.18
    oretical
    -0.17
    èĢģ家
    -0.17
    çĶŁåij½çļĦ
    -0.17
    åħ·ä½ĵçļĦ
    -0.17
    è¿ĻçĤ¹
    -0.16
     positional
    -0.16
    ä½ľåĵģåĨħ容
    -0.16
    å°ļ
    -0.16
    å¼ĢæľĹ
    -0.16
    POSITIVE LOGITS
    à¹Į
    0.20
    ÑĩÑĢежден
    0.18
    ection
    0.18
     à¸ŀฤษ
    0.18
     SimpleName
    0.18
    agnostics
    0.18
     Detaylı
    0.18
     кнопк
    0.17
    èľ¥
    0.17
    ilation
    0.17
    Activations Density 0.636%

    No Known Activations