© 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. 11215
    Prev
    Next
    INDEX
    Explanations

    expressing difficulty or being new

    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
    Secret
    -0.20
    ä½łåı¯ä»¥
    -0.20
     occasional
    -0.19
    ottes
    -0.19
    ↵↵
    -0.19
    ecret
    -0.19
    ä½łä¼ļ
    -0.19
    udos
    -0.19
    ä½łåĸľæ¬¢
    -0.19
    oure
    -0.19
    POSITIVE LOGITS
    解åĨ³éĹ®é¢ĺ
    0.27
    èĩªåѦ
    0.24
    æ±ĤåĬ©
    0.23
    èĩªä¹ł
    0.23
    解åĨ³
    0.21
    æĹłåĬ©
    0.21
    çŀ³
    0.21
    .obtain
    0.21
    .stamp
    0.20
    头çļ®
    0.20
    Activations Density 1.532%

    No Known Activations