© 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. 10708
    Prev
    Next
    INDEX
    Explanations

    future actions or states

    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
    æĽ´æĺ¯
    -0.22
    	RTLR
    -0.22
    æĿĵ
    -0.21
     iNdEx
    -0.20
    rous
    -0.20
    	iNdEx
    -0.19
    éĢ¢
    -0.19
     Gaw
    -0.19
    CALLTYPE
    -0.19
    eward
    -0.19
    POSITIVE LOGITS
    éļıåį³
    0.27
    ä¸Ģ个æĸ°çļĦ
    0.26
    ç«ĭåĪ»
    0.25
    ç«ĭåį³
    0.25
    éļıä¹ĭ
    0.24
    ä¸ĭæĿ¥
    0.24
    ä½łå°±
    0.24
    ä½łåºĶ该
    0.23
    å°±ä¼ļ
    0.23
    åĩºæĿ¥
    0.23
    Activations Density 0.137%

    No Known Activations