© 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. 10748
    Prev
    Next
    INDEX
    Explanations

    return to / late to / added to

    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
    _DOT
    -0.22
    _STORAGE
    -0.20
     Storage
    -0.20
     renov
    -0.20
    æĨ§æĨ¬
    -0.19
    å©ļåIJİ
    -0.19
    建æĪIJåIJİ
    -0.19
     Directions
    -0.19
     Haj
    -0.18
    æ¯ıå¹´
    -0.18
    POSITIVE LOGITS
    ä¸ŃéĢĶ
    0.25
    æīĵæĸŃ
    0.23
    éļ¨æĻĤ
    0.23
    éļıæŶ
    0.23
    æĽ¿æį¢
    0.22
    æĹłç¼Ŀ
    0.22
    å¹²æī°
    0.21
    Åijs
    0.21
    æĮĤçīĮ
    0.20
     throughout
    0.20
    Activations Density 0.123%

    No Known Activations