© 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. 12930
    Prev
    Next
    INDEX
    Explanations

    quality control and assurance

    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
    å¼ĢæĿ¥
    -0.21
    USAGE
    -0.21
    tons
    -0.20
    使çĶ¨æĿĥ
    -0.20
     Amen
    -0.19
    读æĩĤ
    -0.19
    çĩ§
    -0.19
    sWith
    -0.18
    åĤĢ
    -0.18
    Moved
    -0.18
    POSITIVE LOGITS
    ä½ĵ系建设
    0.30
    管çIJĨä½ĵç³»
    0.26
    ä¹ĭè·¯
    0.22
    æ´ĩ
    0.20
    管çIJĨåĴĮ
    0.20
    管çIJĨå·¥ä½ľ
    0.20
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    0.19
    æݪæĸ½
    0.19
    éĻĽ
    0.19
    å·¥ç¨ĭè´¨éĩı
    0.19
    Activations Density 0.031%

    No Known Activations