© 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. 11303
    Prev
    Next
    INDEX
    Explanations

    For the

    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
    thon
    -0.19
     ®
    -0.18
    æĿĥ
    -0.18
     crossorigin
    -0.18
    ç¼ĩ
    -0.18
    adian
    -0.18
     Nunes
    -0.17
    éģij
    -0.17
    åĨįåĪ°
    -0.17
    æ¯Ķèµ·
    -0.17
    POSITIVE LOGITS
    çİĭåŃIJ
    0.22
    èĥŀ
    0.19
    _losses
    0.19
    åīĶ
    0.18
    .om
    0.18
    aki
    0.18
    éĴ¢éĵģ
    0.18
    æĺ¯åIJ¦åŃĺåľ¨
    0.18
    ä¸ĢåĪĻ
    0.17
     Likes
    0.17
    Activations Density 0.001%

    No Known Activations