© 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. 15644
    Prev
    Next
    INDEX
    Explanations

    sparkling wines spirits blend

    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
    çī§åľº
    -0.20
    slice
    -0.20
    озв
    -0.19
     Sinai
    -0.19
    _MISC
    -0.19
    å¹²é¢Ħ
    -0.19
    太快
    -0.19
    æĬĵ
    -0.19
    社ä¼ļåĮĸ
    -0.19
    _wire
    -0.18
    POSITIVE LOGITS
    èģĶ社
    0.21
    tog
    0.21
    ç§ĺ
    0.20
    idend
    0.20
     AppComponent
    0.19
    å·¥èīº
    0.19
    -caption
    0.19
    å®ŀåĬĽ
    0.19
    .Inner
    0.19
    ernes
    0.18
    Activations Density 0.004%

    No Known Activations