© 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. 16670
    Prev
    Next
    INDEX
    Explanations

    adv-ly or -ally or -ering endings

    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
    IQ
    -0.18
    Ø·Ùģ
    -0.18
    æľºéģĩ
    -0.17
    æĬĢæľ¯åĴĮ
    -0.17
    èĭ¥å¹²
    -0.17
     DRV
    -0.16
    éĦļ
    -0.16
    辨åĪ«
    -0.16
    æĥħåĨµ
    -0.16
    åij³
    -0.16
    POSITIVE LOGITS
    èµŀåIJĮ
    0.21
    edly
    0.21
    æĭ¥æĬ¤
    0.20
    osi
    0.20
    bred
    0.20
    åľ°è¯´
    0.20
    éĻĪè¿°
    0.19
    arters
    0.19
    emente
    0.19
     support
    0.18
    Activations Density 0.020%

    No Known Activations