© 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. 14232
    Prev
    Next
    INDEX
    Explanations

    opening, opportunity, accessible, surprise

    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
    å¹´è½»
    -0.23
    æ¯ĵ
    -0.19
    æĿĸ
    -0.19
    ÑĦоÑĢ
    -0.19
    æ³ķåºŃ
    -0.19
    è´±
    -0.19
    çīĩåŃIJ
    -0.19
    åĮ¿åIJį
    -0.18
    ÑĢаÑģÑĤ
    -0.18
    æīĵ好
    -0.18
    POSITIVE LOGITS
    ters
    0.20
     conditions
    0.20
    椹
    0.19
    ioni
    0.19
    æľºä¼ļ
    0.19
    åĦ
    0.18
    memberof
    0.17
    ãĤĤãģªãģĦ
    0.17
    ä¸įåŃĺåľ¨
    0.17
     opportunities
    0.17
    Activations Density 0.009%

    No Known Activations