© 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. 12433
    Prev
    Next
    INDEX
    Explanations

    employee benefits and conditions

    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
    unique
    -0.20
    ç«ĭéĿ¢
    -0.19
    çļĦé«ĺ度
    -0.19
    å°ĸ
    -0.19
    水管
    -0.19
    otec
    -0.18
    à¹ģà¸Ļว
    -0.18
     заÑĤ
    -0.18
    _curve
    -0.18
    lyn
    -0.18
    POSITIVE LOGITS
    adi
    0.21
    éŀį
    0.20
    anh
    0.20
    ourced
    0.20
    ampo
    0.19
     Lan
    0.19
     Revel
    0.18
    鼳
    0.18
    pired
    0.18
    alo
    0.18
    Activations Density 0.021%

    No Known Activations