© 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. 15632
    Prev
    Next
    INDEX
    Explanations

    saving time

    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
    åı°é£İ
    -0.20
    ulk
    -0.19
    åijµåijµ
    -0.18
    ench
    -0.18
    æīĭæĦŁ
    -0.18
    ÑģÑĤвеннÑĭй
    -0.18
    ä¸įä¿¡
    -0.17
    avan
    -0.17
    ä¸įæľį
    -0.17
    æĸ°éĹ»ä¸Ńå¿ĥ
    -0.17
    POSITIVE LOGITS
    åĴĮ社ä¼ļ
    0.21
    为主è¦ģ
    0.19
    åĴĮæĬĢæľ¯
    0.19
    åĴĮ
    0.19
     ult
    0.18
    AndPassword
    0.18
    kh
    0.18
     and
    0.18
    å·¡
    0.17
    ç©Ĺ
    0.17
    Activations Density 0.018%

    No Known Activations