© 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. 14117
    Prev
    Next
    INDEX
    Explanations

    Addresses and greetings

    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
    å¼¹æĢ§
    -0.21
    hee
    -0.20
    elastic
    -0.19
    çŁ¥å·±
    -0.19
     Elastic
    -0.19
    vore
    -0.18
    quit
    -0.18
     elastic
    -0.18
    éĶĭ
    -0.18
     пиÑĤаниÑı
    -0.17
    POSITIVE LOGITS
    ä¹ĭéĻħ
    0.19
    éĻį临
    0.19
     lul
    0.19
    è¿ĻéĩĮæĺ¯
    0.19
    èĪĪ
    0.19
    è¿Ļå°±æĺ¯
    0.18
    第ä¸Ģ次
    0.18
     superv
    0.18
    åĭĻ
    0.18
     tent
    0.17
    Activations Density 0.012%

    No Known Activations