© 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. 13868
    Prev
    Next
    INDEX
    Explanations

    numbers appearing after prefix `o `

    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
    æ®´
    -0.23
    éĿ³
    -0.20
    ä¸Ģä¼ļåĦ¿
    -0.20
    ä¿İ
    -0.19
    èµĦæºIJä¼ĺåĬ¿
    -0.19
    车åĨħ
    -0.19
    =search
    -0.18
    èłķ
    -0.18
     Ñıн
    -0.18
    éĽ¶é£Ł
    -0.18
    POSITIVE LOGITS
    æī©å¼ł
    0.23
    主ä¹īæĢĿæĥ³
    0.21
    æī©
    0.19
     Carey
    0.18
    iton
    0.18
    pare
    0.18
     expansions
    0.18
     widest
    0.18
    åĽĽå¤Ħ
    0.18
     expansion
    0.17
    Activations Density 0.088%

    No Known Activations