© 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. 14424
    Prev
    Next
    INDEX
    Explanations

    many times or countless objectives

    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
    å¾Īå¼Ģå¿ĥ
    -0.22
    æĮºå¥½
    -0.20
    æ´¹
    -0.20
    å¾Īæĺ¯
    -0.20
    究
    -0.19
    çłĿ
    -0.19
     Tits
    -0.18
    åĻªéŁ³
    -0.18
    å¾Īä¸įéĶĻ
    -0.18
    å¾Īæľī
    -0.18
    POSITIVE LOGITS
    æĹłæķ°æ¬¡
    0.35
     countless
    0.28
    ä¸Ģéģį
    0.27
     times
    0.26
    æĹłæķ°
    0.26
    次æķ°
    0.25
    äºĨå¤ļå°ij
    0.23
    -times
    0.23
    å¤ļå°ij
    0.21
    大大å°ıå°ı
    0.20
    Activations Density 0.034%

    No Known Activations