© 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. 11845
    Prev
    Next
    INDEX
    Explanations

    reviews and ratings

    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
    å¾Ĺ天
    -0.23
    é¢ĦæĬ¥
    -0.20
    ç¿Ľ
    -0.20
    æĺ¼
    -0.20
    åĩºæīĭ
    -0.20
    ä¿Ŀè´¹
    -0.19
    èµĥ
    -0.19
    åĨłåĨĽ
    -0.19
    é¢ĦåĶ®
    -0.19
    å¤ļä¸ªåĽ½å®¶
    -0.19
    POSITIVE LOGITS
    angen
    0.22
    ÑĪа
    0.20
     CSL
    0.18
    鹦
    0.18
    .hy
    0.18
    @a
    0.18
    JA
    0.18
    alon
    0.18
    assen
    0.18
     Wonderful
    0.18
    Activations Density 0.001%

    No Known Activations