© 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. 15972
    Prev
    Next
    INDEX
    Explanations

    by 2030, 2050, century

    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
    äºĺ
    -0.20
    è¶Ĭå¤ļ
    -0.19
    elly
    -0.19
    åĩłå®¶
    -0.19
    jis
    -0.19
    樵
    -0.18
    è¿ĩçļĦ
    -0.18
     manh
    -0.18
    -handed
    -0.17
     lifelong
    -0.17
    POSITIVE LOGITS
    åħļåĴĮ
    0.19
     <%=
    0.19
    cedes
    0.18
    ecure
    0.18
    chal
    0.18
    çľ¼ä¸Ń
    0.18
    æĪĺçķ¥
    0.17
    à¸ģà¸ģ
    0.17
    åħħ满
    0.17
    oters
    0.17
    Activations Density 0.007%

    No Known Activations