© 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. 12786
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

    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
     ÐIJлекÑģан
    -0.29
     ÐŁÐ¾Ñĩем
    -0.24
     ÐĶмиÑĤÑĢ
    -0.21
    åĩ«
    -0.19
     zoek
    -0.18
    çļĦ主é¢ĺ
    -0.18
     Sesso
    -0.18
    è¿Ļ两ç§į
    -0.18
    ãģªãģĬ
    -0.18
    è¯Ŀé¢ĺ
    -0.18
    POSITIVE LOGITS
    ero
    0.19
    ITION
    0.18
    ergency
    0.18
    PCODE
    0.17
    ä¾Ī
    0.17
    è¬Ĥ
    0.17
    rack
    0.17
    erator
    0.17
    çĤ¸
    0.17
    inue
    0.17
    Activations Density 0.132%

    No Known Activations