© 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. 16617
    Prev
    Next
    INDEX
    Explanations

    severe conditions

    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
    使ä¹ĭ
    -0.24
     ëĮĢíĨµ
    -0.23
     ìĬ¤ìĬ¤
    -0.21
    наÑĨионалÑĮн
    -0.20
    пÑĢакÑĤик
    -0.20
    ÑĩÑĢежден
    -0.20
    ÑĢеги
    -0.20
    å¼ķæĵİ
    -0.19
    íĹĢ
    -0.19
    (EIF
    -0.19
    POSITIVE LOGITS
    -ish
    0.19
    /high
    0.19
     ÑĤÑĢÑĥд
    0.19
    veis
    0.19
    /month
    0.19
     ÑĢазв
    0.19
     BaseService
    0.18
    ä¸ĢæľŁ
    0.18
    æ¼Ń
    0.18
    éĻ§
    0.18
    Activations Density 0.230%

    No Known Activations