© 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. 13349
    Prev
    Next
    INDEX
    Explanations

    percentage off orders

    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
     tre
    -0.19
     trauma
    -0.19
    究
    -0.19
    estate
    -0.18
     trib
    -0.18
     sober
    -0.17
    bic
    -0.17
    è±Ĩçĵ£
    -0.17
    bral
    -0.17
    bers
    -0.17
    POSITIVE LOGITS
    é¢Ŀå¤ĸ
    0.21
    éĥ¯
    0.21
    é«ĺæĺĤ
    0.20
    强åĬ²
    0.19
    å¿ĥåĬ¨
    0.19
    åŁºå»º
    0.19
    个æľĪåĨħ
    0.19
    Invoker
    0.19
    追赶
    0.19
    é¦ĸ次
    0.19
    Activations Density 0.024%

    No Known Activations