© 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. 11639
    Prev
    Next
    INDEX
    Explanations

    Bravo

    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
    ings
    -0.20
    ighth
    -0.18
    byname
    -0.17
    ãģĦãģ¾ãģĻãģĮ
    -0.17
    apper
    -0.17
    鸦
    -0.16
    awa
    -0.16
    æĬ¤èº«
    -0.16
    imes
    -0.16
    ensen
    -0.16
    POSITIVE LOGITS
    è¿Ń
    0.17
     Ñģобой
    0.17
    _DU
    0.17
    åľºéĿ¢
    0.16
    æł·çļĦ
    0.16
    没éĶĻ
    0.15
    èĩ³ä¸Ĭ
    0.15
    paired
    0.15
    urs
    0.15
    eration
    0.15
    Activations Density 0.003%

    No Known Activations