© 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. 14102
    Prev
    Next
    INDEX
    Explanations

    vowel characters and umlauts

    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
    çĪµ
    -0.24
    éĢ®
    -0.21
    æ³īæ°´
    -0.20
     Steele
    -0.19
    çħ¤çŁ¿
    -0.18
    çŁ¿
    -0.18
    éŀ£
    -0.18
    大çIJĨçŁ³
    -0.17
    tree
    -0.17
    ç«ł
    -0.17
    POSITIVE LOGITS
     vowels
    0.23
    饱满
    0.23
    åŃļ
    0.23
    åĦ¿
    0.20
    èī
    0.20
    èĩªå¦Ĥ
    0.20
    /ros
    0.19
    пÑĢоÑģ
    0.19
    æĺİæľĹ
    0.19
    ught
    0.19
    Activations Density 0.034%

    No Known Activations