© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12290
    Prev
    Next
    INDEX
    Explanations

    returning to lineup

    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
     cons
    -0.22
    类似
    -0.20
    åķ»
    -0.19
    æŁ¬
    -0.19
     rig
    -0.19
    è¿ĻåĿĹ
    -0.18
    ä»ĸä¹Ł
    -0.18
    ä»ĸ认为
    -0.18
    æĸĩæľ¬
    -0.18
     lever
    -0.18
    POSITIVE LOGITS
     Ñģнова
    0.21
    åĨį次
    0.21
    çµĤæĸ¼
    0.19
    antro
    0.19
    åıĪ被
    0.19
    åĨįä¸Ģ次
    0.19
    åıĪä¸Ģ次
    0.19
    ľ
    0.19
     Update
    0.19
    åĨį度
    0.18
    Activations Density 0.068%

    No Known Activations