© 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. 15040
    Prev
    Next
    INDEX
    Explanations

    belief and opinion

    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
    è¿ĺä¸įå¦Ĥ
    -0.22
    èĽĽ
    -0.20
    çĤ¬
    -0.20
    åħ³æ³¨åº¦
    -0.20
    æĶ¶å®ĺ
    -0.20
    ignite
    -0.20
    çļĦ身份
    -0.19
    çľĭä¼¼
    -0.19
    æĿ¥å®¾
    -0.18
    IGN
    -0.18
    POSITIVE LOGITS
     hal
    0.26
    认为
    0.24
     philosoph
    0.24
     philosophy
    0.24
    ä¸»å¼ł
    0.23
    çIJĨ念
    0.23
    æıIJåĢ¡
    0.22
    çļĦçIJĨ念
    0.21
     belief
    0.21
     education
    0.21
    Activations Density 0.047%

    No Known Activations