© 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. 11316
    Prev
    Next
    INDEX
    Explanations

    make, generally, commute, prepare, generate, improve

    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
    äºĨä»ĸçļĦ
    -0.21
    å¢ŀæ·»äºĨ
    -0.20
    æ¶Ī失äºĨ
    -0.19
    ä»ĸå·²ç»ı
    -0.19
    åĽŀæĿ¥äºĨ
    -0.19
    äºĨåĩºæĿ¥
    -0.18
    æijĩäºĨ
    -0.18
    èµĥ
    -0.18
     Äijã
    -0.18
    ç»ĻäºĨæĪij
    -0.18
    POSITIVE LOGITS
    èİ·å¾Ĺ
    0.33
    è¿Ľè¡Į
    0.32
    å®ŀçİ°
    0.30
    使
    0.29
    èİ·åıĸ
    0.28
    æī¾åĩº
    0.28
    æī¾åĪ°
    0.28
    æĬĬ
    0.26
    æıIJä¾Ľ
    0.26
    å¢ŀåĬł
    0.26
    Activations Density 0.324%

    No Known Activations