© 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. 12737
    Prev
    Next
    INDEX
    Explanations

    reported, revealed, alleges

    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
    ided
    -0.21
    æ¸IJ
    -0.19
     Kaiser
    -0.18
    lap
    -0.18
     lap
    -0.18
    åĪĽå»ºå·¥ä½ľ
    -0.18
     scand
    -0.18
    æļĩ
    -0.17
    å¡ŀ
    -0.17
    iere
    -0.17
    POSITIVE LOGITS
    åĪ°åºķ
    0.19
    omm
    0.18
    æ¦ĤåĨµ
    0.18
    ç¡IJ
    0.18
    究竣
    0.18
    èĥ¥
    0.18
    ç¾Ĭæ¯Ľ
    0.18
    .md
    0.18
    åħļçļĦ建设
    0.17
    LAT
    0.17
    Activations Density 0.629%

    No Known Activations